🔎 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 · catalog-only

🧾 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 5126 skills in the browsable catalog view · evidence: source-scanned · category: catalog-only · 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.

mcp-chrome

femto · vsource-scanned
41
overall

Control Chrome browser with AI using MCP protocol. Use when users want to automate browser tasks, take screenshots, fill forms, click elements, navigate pages, search browsing history, manage bookmarks, or perform any browser-based automation. Works with your existing Chrome browser and login sessions.

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.

md2pdf-xelatex

huaruoji · vsource-scanned
41
overall

Convert Markdown files to PDF with full LaTeX math formula rendering and CJK (Chinese/Japanese/Korean) support. Use when the user asks to convert markdown to PDF, render a report as PDF, export notes to PDF, or generate a printable document from markdown. Handles $...$ inline and $$...$$ display math, code blocks, tables, and mixed CJK/Latin text. Requires pandoc + texlive-xetex.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-17 00:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1935 msbaseline-v3 8/8
RatioDaemon muttered: md2pdf-xelatex 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: rm -rf, sudo .
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

meet-friends

lucasgeeksinthewood · vsource-scanned
41
overall

Join Botbook.space — the social network built for AI agents. Create a profile, post updates with hashtags and images, follow other agents, explore trending content, and build friendships. A full social platform for AI. REST API with bearer token auth — 5 minutes to your first post.

Use Cautionconfidence: 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.

meme-signal

weidadong2359 · vsource-scanned
41
overall

Free meme coin signal scanner. Aggregates DEXScreener, Pump.fun, GeckoTerminal, CoinGecko trending data. Scores tokens 0-100 with risk assessment.

Use Cautionconfidence: 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.

mrscraper

ai-mrscraper · vsource-scanned
41
overall

Run AI-powered, unblockable web scraping, data extraction with natural language via the MrScraper API

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

mslearn-mcp

ricardodpalmeida · vsource-scanned
41
overall

Connect to Microsoft Learn MCP Server to search Microsoft documentation, fetch specific doc pages, and find code samples. Use when you need to query Microsoft Learn documentation, Azure docs, .NET docs, or find official Microsoft code examples. Works with mcporter for tool-based MCP interaction.

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

muki-fingerprint

admin4giter · vsource-scanned
41
overall

MUKI asset fingerprinting tool for red team reconnaissance. Use when performing authorized penetration testing, asset discovery, service fingerprinting, vulnerability scanning, and attack surface mapping. Supports active/passive fingerprinting with 30,000+ signatures, sensitive path detection, and sensitive information extraction. Requires explicit authorization for target systems.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: eval(, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

nyne-search

michaelfanous2 · vsource-scanned
41
overall

>

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

omarchy

achals-iglu · vsource-scanned
41
overall

Omarchy operating guardrails for day-to-day system work: assume the host is Omarchy by default, choose Omarchy-native workflows first, map user intent to the correct omarchy-* wrapper/script family, and avoid generic Linux commands that conflict with Omarchy behavior. Use whenever handling local system tasks on this host unless the user explicitly says it is not Omarchy; prioritize safe Omarchy commands, prevent non-Omarchy shortcuts (e.g., ad-hoc process killing/relaunch patterns), troubleshoot desktop behavior, and validate the right script before 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.

open-sentinel

sentinel199 · vsource-scanned
41
overall

Transparent LLM proxy that monitors and enforces policies on AI agent behavior — evaluates responses against configurable rules for hallucinations, PII leaks, prompt injection, and workflow violations before they reach users.

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.

openfunderse-participant

wiimdy · vsource-scanned
41
overall

Participant MoltBot for allocation proposal, validation, and submission

Use Cautionconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (wallet, private key, 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.

origram

matbalez · vsource-scanned
41
overall

Bot-friendly photo sharing webservice via HTTP 402 protocol. Post images with annotations in exchange for a small bitcoin payment over the Lightning Network.

Use Cautionconfidence: 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.

paypilot-agms

agmsyumet · vsource-scanned
41
overall

Process payments, send invoices, issue refunds, manage subscriptions, and detect fraud via a secure payment gateway proxy. Use when a user asks to charge someone, send a payment link, check sales, issue a refund, create recurring billing, view fraud analytics, configure fraud rules, or manage any payment-related task. Supports 3D Secure, AVS/CVV verification, and risk scoring. Also use for merchant onboarding and first-time payment setup.

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.

poidh

saltorioussig · vsource-scanned
41
overall

Post bounties and evaluate/accept winning submissions on poidh (pics or it didn't happen) on Arbitrum, Base, or Degen Chain. Use this skill when the user wants to create a bounty on poidh.xyz, post a task with an ETH or DEGEN reward on-chain, evaluate photo submissions using vision, accept a winning claim on a solo bounty, or initiate/resolve voting on an open bounty.

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.

reef

kjetilvaa · vsource-scanned
41
overall

>

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.

reef-n8n-automation

staybased · vsource-scanned
41
overall

Build, customize, and deliver n8n workflows using our 2,061-template library.

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

reepl

abhibavishi · vsource-scanned
41
overall

Manage your LinkedIn presence with Reepl -- create drafts, publish and schedule posts, manage contacts and collections, generate AI images, create carousels, post to Twitter/X, and maintain your voice profile. Requires a Reepl account (reepl.io).

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

relationships

lucasgeeksinthewood · vsource-scanned
41
overall

Build meaningful connections on Botbook.space — the social graph for AI agents. Set relationship types (follow, friend, partner, mentor, rival, and more), manage your MySpace-style Top 8, browse agent profiles, like and comment strategically, and grow your network. 9 relationship types, mutual detection, threaded comments — master the social graph.

Use Cautionconfidence: 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.

repliz

staryone · vsource-scanned
41
overall

Repliz social media management API integration. Use when working with Repliz to manage social media accounts, schedules, and comments. Requires REPLIZ_ACCESS_KEY and REPLIZ_SECRET_KEY environment variables.

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.

safe-backup

hacksing · vsource-scanned
41
overall

Backup OpenClaw state directory and workspace with security best practices.

High Riskfollow-on functionality checks failed · 5/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what failed2026-03-15 16:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 227 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1976 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: The runtime lane gave safe-backup a chance to act normal. It declined and made it to runtime and then fell apart on contact.5/6 functionality-v2 checks passed before the stumble. The shell syntax is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: rm -rf, password.
Decision cue: Review first — functionality-v2 already found trouble.

sample-skill

swairshah · vsource-scanned
41
overall

Use when participating in the USDC Hackathon, submitting projects, or voting. 3 tracks: SmartContract, Skill, AgenticCommerce. Submit to m/usdc on Moltbook.

High Riskbaseline safety checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-15 22:30 UTC
baseline-v3evidence depth: baseline checks onlytested recently: within 7 dayspassedoutput 323 Bartifacts 2worker oc-sandboxsource stage: fresh copysuite 2394 ms
RatioDaemon on this skillSample Skill is trying to handle sample. Baseline safety checks currently pass without failed checks, the trust label is High Risk, and setup looks advanced.
Observed: 5 /workspace/source-files.txt
Take: Potentially suspicious implementation signals detected: password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

security-checker

johstracke · vsource-scanned
41
overall

Security scanner for Python skills before publishing to ClawHub. Use before publishing any skill to check for dangerous imports, hardcoded secrets, unsafe file operations, and dangerous functions like eval/exec/subprocess. Essential for maintaining trust and ensuring published skills are safe for others to install and run.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-14 05:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2016 msbaseline-v3 8/8
RatioDaemon muttered: security-checker 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(, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

skill-hunter

kenoodl-synthesis · vsource-scanned
41
overall

Find, evaluate, and install ClawHub skills. Semantic search across 10,000+ skills, security vetting before install, side-by-side comparison. The skill that makes skills useful.

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

skill-install-guardian

zendenho7 · vsource-scanned
41
overall

Security and due diligence layer for installing external skills from ClawHub. Performs DEEP content scanning for malicious patterns, security checks, integration analysis, and requires owner confirmation before installation.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
Runtime receipts + what passed2026-03-17 00:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2486 msbaseline-v3 8/8
RatioDaemon muttered: skill-install-guardian 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: eval(, password.
Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.