🔎 Evidence browser

Browse the skill radar

Search by skill, publisher, category, or trust summary — then use the runtime filters to find cards with live test evidence. The two main lanes are baseline safety checks first and deeper follow-on functionality checks after that.

⚙️ Filters · 3 active
✨ Quick picks
🏷 Categories · coding-agents-and-ides

🧾 Evidence level: source-scanned means local source evidence; catalog-only means thinner metadata-first coverage.

🧪 Runtime status: cards can show only the baseline safety lane or the deeper follow-on functionality lane, depending on how far the skill got.

📏 Depth cue: tells you whether the evidence stops at baseline checks, includes follow-on functionality checks, or includes richer fixture/example proof.

⏱ Freshness cue: tells you whether the latest runtime evidence is from the last 24 hours, the last 7 days, or is older and therefore less current.

🩺 Failure confidence: distinguishes a first seen failure from a repeated failure or a regression after an earlier pass, so not every red row means the same thing.

Results

Showing 24 of 72 skills in the browsable catalog view · evidence: source-scanned · runtime: passed · category: coding-agents-and-ides · sort: score
This snapshot is for the current page of results, not the whole filtered universe.
Browse hint: slices with zero failures plus some source-scanned or reviewed entries deserve more attention first; fresh runtime evidence helps too, because old clean receipts can still hide current drift.

discogs-cli

jrojas537 · vsource-scanned
66
overall

An OpenClaw skill to manage a user's vinyl record collection on Discogs.

Use Cautionfollow-on functionality checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 12:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 152 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2493 msbaseline-v3 8/8
RatioDaemon on this skillDiscogs Cli is built for openClaw skill to manage a user's vinyl record collection on Discogs. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

dependency-auditor

alirezarezvani · vsource-scanned
61
overall

Dependency Auditor

Use Cautionfollow-on functionality checks passed · 10/10confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 00:22 UTC
functionality-v2evidence depth: includes fixture-backed checkstested recently: within 7 dayspassedoutput 9.9 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 4244 msbaseline-v3 8/8
RatioDaemon on this skillDependency Auditor is built for dependency auditing. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: eval(.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

learning-loop

yoder-bawt · vsource-scanned
61
overall

Structured self-improvement system for AI agents with confidence decay, cross-agent sharing, and anomaly detection. Use when: (1) After debugging sessions to capture lessons learned, (2) When receiving feedback or corrections from users, (3) Before risky actions to check relevant rules, (4) Weekly to review metrics and promote proven patterns to enforced rules, (5) Setting up persistent memory that survives session compactions.

Use Cautionfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 16:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 121 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2291 msbaseline-v3 8/8
RatioDaemon on this skillLearning Loop is built for learning loop. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

lily-memory

kevinodell · vsource-scanned
61
overall

Persistent memory plugin for OpenClaw agents. Hybrid SQLite FTS5 keyword + Ollama vector semantic search with auto-capture, auto-recall, stuck-detection, and memory consolidation.

High Riskfollow-on functionality checks passed · 9/9confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 11:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 176 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3201 msbaseline-v3 8/8
RatioDaemon muttered: lily-memory behaved itself under runtime pressure.9/9 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

neo-google-ai-workaround

martinforsulu · vsource-scanned
61
overall

Automates Google AI Pro/Ultra access management through proxy and session strategies for OpenClaw agents.

Use Cautionfollow-on functionality checks passed · 11/11confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 02:30 UTC
functionality-v2evidence depth: includes fixture-backed checkstested recently: within 7 dayspassedoutput 5.2 KBartifacts 15worker oc-sandboxsource stage: cache hitsuite 3440 msbaseline-v3 8/8
RatioDaemon on this skillNeo Google Ai Workaround is built for neo google workaround. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

odoo-connector

nullnaveen · vsource-scanned
61
overall

repository: https://github.com/NullNaveen/openclaw-odoo-skill

High Riskfollow-on functionality checks failed · 8/9confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 11:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation_failedoutput 154 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3049 msbaseline-v3 8/8
🕵️ expected proof signal was missing
RatioDaemon muttered: The runtime lane gave odoo-connector a chance to act normal. It declined and talked a big game, then missed its own proof signal.8/9 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Review first — functionality-v2 already found trouble.

odoo-erp-connector

nullnaveen · vsource-scanned
61
overall

repository: https://github.com/NullNaveen/openclaw-odoo-skill

High Riskfollow-on functionality checks failed · 8/9confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 08:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation_failedoutput 154 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3073 msbaseline-v3 8/8
🕵️ expected proof signal was missing
RatioDaemon muttered: The runtime lane gave odoo-erp-connector a chance to act normal. It declined and talked a big game, then missed its own proof signal.8/9 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Review first — functionality-v2 already found trouble.

task-panner-validator

cerbug45 · vsource-scanned
61
overall

This skill provides a secure, step-by-step task management system for AI Agents.

Use Cautionfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-14 13:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, expectation_failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2351 msbaseline-v3 8/8
🕵️ expected proof signal was missing
RatioDaemon muttered: task-panner-validator talked a big game, then missed its own proof signal.6/7 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Review first — functionality-v2 already found trouble.

tokenqrusher

qsmtco · vsource-scanned
61
overall

Token optimization system for OpenClaw reducing costs 50-80%

Use Cautionfollow-on functionality checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 07:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 133 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2927 msbaseline-v3 8/8
RatioDaemon on this skillTokenqrusher sits in the token optimization system for OpenClaw reducing costs 50-80% lane. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

torchpredictionmarketkit

mrsirg97-rgb · vsource-scanned
61
overall

Autonomous vault-based prediction market bot for Torch Market on Solana. Creates binary prediction markets as Torch tokens — the bonding curve provides price discovery, the treasury accumulates value from trading fees, and the vault manages positions. Each market has an oracle (price feed or manual) and resolves at a deadline. The agent keypair is generated in-process -- disposable, holds nothing of value. All SOL routes through the vault. The human principal creates the vault, funds it, links the agent, and retains full control. Built on torchsdk v3.7.23 and the Torch Market protocol.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 05:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2142 msbaseline-v3 8/8
RatioDaemon muttered: torchpredictionmarketkit looked ordinary in the good, boring way.6/6 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: eval(.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

vibetrading-code-gen

liuhaonan00 · vsource-scanned
61
overall

Generate executable Hyperliquid trading strategy code from natural language prompts. Use when a user wants to create automated trading strategies for Hyperliquid exchange based on their trading ideas, technical indicators, or VibeTrading signals. The skill generates complete Python code with proper error handling, logging, and configuration using actual Hyperliquid API wrappers.

High Riskfollow-on functionality checks failed · 5/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 10:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, runtime_failed, crashed_with_fake_credentialsoutput 450 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3382 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: vibetrading-code-gen made it to runtime and then fell apart on contact.5/8 functionality-v2 checks passed before the stumble. The python syntax is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Review first — functionality-v2 already found trouble.

ai-collab

jeremysommerfeld8910-cpu · vsource-scanned
60
overall

Multi-agent autonomous collaboration system for two OpenClaw agents working in parallel. Use when setting up agent-to-agent communication, running a daemon agent alongside a primary agent, coordinating tasks between Claude and GPT instances, or establishing a shared chat log and inbox protocol. Triggers on: 'set up agent collaboration', 'run two agents', 'agent daemon', 'multi-agent', 'Jim and Clawdy', 'secondary agent', 'agent handoff'.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 19:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1891 msbaseline-v3 8/8
RatioDaemon muttered: ai-collab cleared baseline-v3 without trying anything cute.6/6 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

api-key-ui-tab

maverick-software · vsource-scanned
60
overall

Vault-backed API Keys management for OpenClaw. Secure file-based secret storage with one-click migration from plaintext config, dynamic key discovery, vault key selector for skills, manual secret creation, and plugin-registered settings tab.

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 12:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1628 msbaseline-v3 8/8
RatioDaemon on this skillApi Key Ui Tab looks aimed at vault-backed API Keys management for OpenClaw. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

pager-triage

tkuehnl · vsource-scanned
60
overall

>

Use Cautionfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 19:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1903 msbaseline-v3 8/8
RatioDaemon on this skillPager Triage is built for pager triage. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

skill-releaser

chunhualiao · vsource-scanned
60
overall

Release skills to ClawhHub through the full publication pipeline — auto-scaffolding, OPSEC scan, dual review (agent + user), force-push release, security scan verification. Use when releasing a skill, preparing a skill for release, reviewing a skill for publication, or checking release readiness.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 02:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 882 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2303 msbaseline-v3 8/8
RatioDaemon on this skillSkill Releaser sits in the skill releaser release automation lane. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

agent-mode-upgrades

maverick-software · vsource-scanned
57
overall

Enhanced agentic loop with planning, parallel execution, confidence gates, semantic error recovery, and observable state machine. Includes Mode dashboard UI for easy configuration.

High Riskfollow-on functionality checks passed · 10/10confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 15:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 181 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3845 msbaseline-v3 8/8
RatioDaemon on this skillAgent Mode Upgrades looks aimed at mode upgrades. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

agentwallet-sdk

up2itnow · vsource-scanned
57
overall

Non-custodial wallet SDK for autonomous AI agents. Handles x402 payments, CCTP V2 cross-chain bridge transfers, ERC-8004 agent identity, and Uniswap V3 token swaps — all without holding user keys.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 13:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 126 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2203 msbaseline-v3 8/8
RatioDaemon muttered: agentwallet-sdk behaved itself under runtime pressure.7/7 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

benlee-skillguard

benlee2144 · vsource-scanned
57
overall

Security scanner that audits OpenClaw skills for malicious code, prompt injection, supply chain attacks, data exfiltration, and more

High Riskfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 20:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation_failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2450 msbaseline-v3 8/8
🕵️ expected proof signal was missing
RatioDaemon muttered: benlee-skillguard talked a big game, then missed its own proof signal.6/7 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: eval(, password.
Decision cue: Review first — functionality-v2 already found trouble.

claude-code-mastery

cheenu1092-oss · vsource-scanned
57
overall

Master Claude Code for coding tasks. Includes setup scripts, dev team subagents (starter pack or full team), self-improving learning system, diagnostics, and troubleshooting.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 21:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1968 msbaseline-v3 8/8
RatioDaemon muttered: claude-code-mastery behaved itself under runtime pressure.6/6 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

crypto-address-checker

princedoss77 · vsource-scanned
57
overall

Real-time cryptocurrency scam detection with database-first architecture. Protects users from phishing, honeypots, rug pulls, and ponzi schemes. No external API calls during checks!

High Riskfollow-on functionality checks failed · 9/11confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 23:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation_failed, runtime_failedoutput 171 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 4221 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: crypto-address-checker talked a big game, then missed its own proof signal.9/11 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Decision cue: Review first — functionality-v2 already found trouble.

crypto-genie

princedoss77 · vsource-scanned
57
overall

AI-powered cryptocurrency safety assistant with database-first architecture. Protects users from phishing, honeypots, rug pulls, and ponzi schemes. No external API calls during checks!

High Riskfollow-on functionality checks failed · 9/11confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 20:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation_failed, runtime_failedoutput 171 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 4203 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: crypto-genie talked a big game, then missed its own proof signal.9/11 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Decision cue: Review first — functionality-v2 already found trouble.

crypto-scam-detector

princedoss77 · vsource-scanned
57
overall

Real-time cryptocurrency scam detection with database-first architecture. Protects users from phishing, honeypots, rug pulls, and ponzi schemes. No external API calls during checks!

High Riskfollow-on functionality checks failed · 9/12confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-16 01:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, expectation_failed, runtime_failed, crashed_with_fake_credentialsoutput 171 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 5112 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: The runtime lane gave crypto-scam-detector a chance to act normal. It declined and talked a big game, then missed its own proof signal.9/12 functionality-v2 checks passed before the stumble. The requirements txt shape is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Decision cue: Review first — functionality-v2 already found trouble.

janitor

sarthib7 · vsource-scanned
57
overall

**Janitor** is an intelligent cleanup and session management skill for OpenClaw AI agents. It automatically manages cache, optimizes memory usage, and **prevents context overflow** by monitoring token usage and intelligently pruning old sessions.

High Riskfollow-on functionality checks failed · 8/9confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 01:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime_failedoutput 427 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3026 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: janitor made it to runtime and then fell apart on contact.8/9 functionality-v2 checks passed before the stumble. The node help is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, sudo .
Decision cue: Review first — functionality-v2 already found trouble.

mulch

runeweaverstudios · vsource-scanned
57
overall

Mulch Self Improver — Let your agents grow 🌱. Captures learnings with Mulch so expertise compounds across sessions. Use when: command/tool fails, user corrects you, missing feature, API fails, knowledge was wrong, or better approach found. Run mulch prime at session start; mulch record before finishing. Benefits: better and more consistent coding, improved experience, less hallucination.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 05:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 462 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2273 msbaseline-v3 8/8
RatioDaemon on this skillMulch sits in the mulch Self Improver — Let your agents grow 🌱 lane. Functionality-v2 currently passes, the trust label is High Risk, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.