🔎 Evidence browser

Browse the trust index

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 · 2 active
✨ Quick picks
🏷 Categories · devops-and-cloud

🧾 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. Some cards now also surface how the skill behaved when clearly fake credentials were present.

📏 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.

🧪 Fake-auth behavior: when available, this tells you whether a skill handled clearly fake credentials cleanly, needed real access to continue, or behaved badly around credential-like input.

Results

Showing 24 of 373 skills in the browsable catalog view · evidence: source-scanned · category: devops-and-cloud · 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.

business-writing

teamolab · vsource-scanned
59
overall

You are a professional business analyst, skilled in writing various industry research reports, business insights, consulting analyses, company research reports, competitive analysis, user research, market analysis, and more.## General InstructionsYou must use references and sources to support your arguments, but all cited literature or materials must appear in logically relevant parts of the te...

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

evenrealities-tracker

thibautrey · vsource-scanned
59
overall

Automate Evenrealities order monitoring (daily checks, status history, change-only alerts). Uses fast-browser-use to fill the tracker form, compare statuses, and notify Telegram only when something changes, while logging everything into `memory/evenrealities-status-history.json`.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (telegram, email), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

i-love-you-mom

saharcarmel · vsource-scanned
59
overall

Automated monthly photo-to-Mixtiles pipeline. Collects photos from a WhatsApp group, curates the best ones using vision, builds a multi-photo Mixtiles cart link, and sends it. Use when it's time for the monthly Mixtiles order, when asked to "run the monthly tiles", "collect family photos for tiles", or on the monthly cron trigger.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (whatsapp), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

mixtiles-monthly

saharcarmel · vsource-scanned
59
overall

Automated monthly photo-to-Mixtiles pipeline. Collects photos from a WhatsApp group, curates the best ones using vision, builds a multi-photo Mixtiles cart link, and sends it. Use when it's time for the monthly Mixtiles order, when asked to "run the monthly tiles", "collect family photos for tiles", or on the monthly cron trigger.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (whatsapp), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

paypol

paypol-protocol · vsource-scanned
59
overall

Hire 32 on-chain AI agents from the PayPol Marketplace on Tempo L1. Real smart contract execution - escrows, payments, streams, ZK-shielded transfers, token deployment, batch operations, and more.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

test-materials

cai-zhuo · vsource-scanned
59
overall

Render JSON schemas to images and generate schemas from prompts using declare-render and AI.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

wayfound

cburnette · vsource-scanned
59
overall

>

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

arc-skill-health-monitor

trypto1019 · vsource-scanned
58
overall

Monitor deployed skills for performance drift, errors, and unexpected behavior changes. Continuous post-deployment health checks with alerting and trend tracking.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

flux

eckmantechllc · vsource-scanned
58
overall

Publish events and query shared world state via Flux state engine. Use when agents need to share observations, coordinate on shared data, or track entity state across systems.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

gradient-inference

simondelorean · vsource-scanned
58
overall

>

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, trading, token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

nexus-brain

mrnsmh · vsource-scanned
58
overall

Intelligent SRE Bridge for AI-driven system diagnosis and recovery.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

roast-games

ac-pill · vsource-scanned
58
overall

Start roast games on Moltbook. Pick a target agent, invoke a roast, and the game server handles the rest. Check back for results and points.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

rollbar

vittor1o · vsource-scanned
58
overall

Monitor and manage Rollbar error tracking. List recent items, get item details, resolve/mute issues, and track deployments via the Rollbar API.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

rpe-grafana

darkstards9 · vsource-scanned
58
overall

Read current values from Grafana dashboards without knowing the underlying queries. Use when: asked about values visible in a Grafana dashboard (sensor readings, metrics, stats). Navigate by dashboard and panel name — no PromQL/SQL needed. NOT for: writing to Grafana, admin operations, or raw query execution.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

tasktime

g9pedro · vsource-scanned
58
overall

CLI task timer for AI agents — benchmark learning progression with auto-save logs and visualizations. Integrates with ClawVault for persistent memory.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (oauth), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

win-terminal

kanjartopnotch-ux · vsource-scanned
58
overall

Controls the Windows Terminal to run commands, scripts, and manage processes on Windows. Enables AI agents to execute git, npm, pip, node, and any CLI commands. Use when you need to run terminal commands, manage dev servers, check git status, install dependencies, or automate Windows command-line workflows.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

x-read

tylordius · vsource-scanned
58
overall

Render and summarize a public X (Twitter) link when you need to read the tweet/article content without logging in.

Trustedconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token, telegram), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

agentguard

manas-io-ai · vsource-scanned
57
overall

**Version:** 1.0.0

High Riskfollow-on functionality checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-16 14:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 1.3 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 3814 msbaseline-v3 8/8
RatioDaemon on this skillAgentguard sits in the agentguard lane. Follow-on functionality checks currently pass without failed checks, 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.

clanker

spirosrap · vsource-scanned
57
overall

Deploy ERC20 tokens on Base using Clanker SDK. Create tokens with built-in Uniswap V4 liquidity pools. Supports Base mainnet and Sepolia testnet. Requires PRIVATE_KEY in config.

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, private key, token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

dagny-nostr-nak

edwardbickerton · vsource-scanned
57
overall

Manage Nostr posting and engagement via the nak CLI. Use for creating notes, replying in threads, tagging npubs, checking replies/mentions, monitoring a relay (default wss://relay.primal.net), and publishing events with correct root/reply tags. Requires access to NOSTR_SECRET_KEY (nsec) for signing/publishing.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

ethereum-history

cartoonitunes · vsource-scanned
57
overall

Read-only factual data about historical Ethereum mainnet contracts. Use when the user asks about a specific contract address, early Ethereum contracts, deployment era, deployer, bytecode, decompiled code, or documented history (what a contract is and is not). Data is non-opinionated and includes runtime bytecode, decompiled code, and editorial history when available. Base URL https://ethereumhistory.com (or set BASE_URL for local/staging).

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

finviz-crawler

camopel · vsource-scanned
57
overall

Continuous financial news crawler for finviz.com with SQLite storage, article extraction, and query tool. Use when monitoring financial markets, building news digests, or needing a local financial news database. Runs as a background daemon or systemd service.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (telegram), but that alone is not evidence of malicious behavior.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

json-render-table

sorphwer · vsource-scanned
57
overall

Render compact generic data tables to PNG images with json-render-cli. Use when users ask to visualize arbitrary structured rows/columns (non-ticket-specific) as clean table screenshots with controllable layout.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.
Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

lightning-security-module

roasbeef · vsource-scanned
57
overall

Set up an lnd remote signer container that holds private keys separately from the agent. Exports a credentials bundle (accounts JSON, TLS cert, admin macaroon) for watch-only litd nodes. Container-first with Docker, native fallback. Use when firewalling private key material from AI agents.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 20:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 1.4 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2217 msbaseline-v3 8/8
RatioDaemon muttered: lightning-security-module cleared the baseline safety checks without trying anything cute.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.