🔎 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 5367 skills in the browsable catalog view · reviewed: no · 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.
Quick guide for newcomers: start by scanning the card badges for runtime passed, source-scanned, and fresh evidence. Then use the decision cue on each card to sort “good first pick” from “needs review” without opening every result.

aioz-ui-v3

datnguyen26730 · vsource-scanned
47
overall

Build UI components and pages using AIOZ UI V3 design system. Use this skill whenever the user wants to create, edit, or style React components using AIOZ UI tokens, Tailwind classes, color tokens, typography utilities, icons from @aioz-ui/icon-react, or chart components (LineChart, AreaChart, BarChart, DonutChart). Trigger on any task involving AIOZ UI components, design tokens like --sf-neu-block or --text-neu-bold, brand colors, typography classes (text-title-01, text-body-02), icon imports, data visualization, or translating Figma MCP output into production-ready code.

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-16 19:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1729 msbaseline-v3 8/8
RatioDaemon muttered: aioz-ui-v3 looked ordinary in the good, boring way.5/5 functionality-v2 checks passed. Pleasantly boring.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

aisa-twitter-skill

bowen-dotcom · vsource-scanned
47
overall

**Twitter/X data access and automation for autonomous agents. Powered by AIsa.**

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

apipick-email-checker

javainthinking · vsource-scanned
47
overall

Validate email addresses using the apipick Email Validator API. Performs syntax checking, MX record verification, and disposable/throwaway email detection. Use when the user wants to verify an email address, check if an email domain exists and can receive mail, detect disposable or temporary emails, or validate email format. Requires an apipick API key (x-api-key). Get a free key at https://www.apipick.com.

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

appdeploy

avimak · vsource-scanned
47
overall

Deploy web apps with backend APIs, database, file storage, AI operations, authentication, realtime, and cron jobs. Use when the user asks to deploy or publish a website or web app and wants a public URL. Uses HTTP API via curl.

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

arccos-golf

pfrederiksen · vsource-scanned
47
overall

Analyze Arccos Golf performance data including club distances, strokes gained metrics, scoring patterns, and round-by-round performance. Use when the user asks about golf statistics, club recommendations, performance trends, or wants detailed analysis from their Arccos Golf sensors.

Use Cautionfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-15 02:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2479 msbaseline-v3 8/8
RatioDaemon on this skillArccos Golf is trying to handle arccos golf. Follow-on functionality checks currently pass without failed checks, the trust label is Use Caution, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

audio-reply

matrixy · vsource-scanned
47
overall

Generate audio replies using TTS. Trigger with "read it to me [public URL]" to fetch and read content aloud, or "talk to me [topic]" to generate a spoken response. Also responds to "speak", "say it", "voice reply".

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

audio-visualization

eftalyurtseven · vsource-scanned
47
overall

Generate audio visualization videos using each::sense AI. Create waveforms, spectrum analyzers, particle effects, 3D visualizations, and beat-synced animations from audio files.

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

auteng-docs

operator-auteng-ai · vsource-scanned
47
overall

Publish technical docs with Mermaid diagrams, KaTeX math, and code highlighting. Persistent workspace, shareable links, versioning. Free.

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

auto-whisper-safe

neal-collab · vsource-scanned
47
overall

RAM-safe voice transcription with auto-chunking — works on 16GB machines without crashes

Use Cautionfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-15 10:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1933 msbaseline-v3 8/8
RatioDaemon muttered: auto-whisper-safe 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.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

bagman

zscole · vsource-scanned
47
overall

Secure key management for AI agents. Use when handling private keys, API secrets, wallet credentials, or when building systems that need agent-controlled funds. Covers secure storage, session keys, leak prevention, prompt injection defense, and MetaMask Delegation Framework integration.

High Riskbaseline safety checks passed · 8/8confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-16 20:30 UTC
baseline-v3evidence depth: baseline checks onlytested recently: within 7 daysfake-auth behavior: handled cleanlypassed, handled fake credentials cleanlyoutput 484 Bartifacts 2worker oc-sandboxsource stage: fresh copysuite 2422 ms
fake-auth behavior: handled cleanlyClearly fake credentials were exercised and handled normally.
RatioDaemon on this skillBagman sits in the secure key management for AI agents lane. Baseline safety checks currently pass without failed checks, the trust label is High Risk, and setup looks advanced.
Observed: 8 /workspace/source-files.txt
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

bilibili-youtube-watcher

donnycui · vsource-scanned
47
overall

Fetch and read transcripts from YouTube and Bilibili videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

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

boltzpay

leventilo · vsource-scanned
47
overall

Pay for API data automatically — multi-protocol (x402 + L402), multi-chain

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

calibre-metadata-apply

nextaltair · vsource-scanned
47
overall

Apply metadata updates to existing Calibre books via calibredb over a Content server. Use for controlled metadata edits after target IDs are confirmed by a read-only lookup.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-15 15:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 97 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2138 msbaseline-v3 8/8
RatioDaemon muttered: calibre-metadata-apply 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: sudo , password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

camoufox

goodgoodjm · vsource-scanned
47
overall

Anti-detect browser automation using Camoufox (Firefox-based). Use instead of Chrome/Playwright for bot-detection-heavy sites like X/Twitter, Naver, and other protected sites. Provides stealth browsing with OS/browser fingerprint spoofing, humanized mouse movements, and persistent sessions.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: sudo , password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

cetus

k66inthesky · vsource-scanned
47
overall

This guide covers all Cetus SDK v2 packages for building DeFi applications on Sui.

Insufficient Evidenceconfidence: 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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

clangd-lsp

bowen31337 · vsource-scanned
47
overall

C/C++ language server (clangd) providing code intelligence, diagnostics, and formatting for .c, .h, .cpp, .cc, .cxx, .hpp, .hxx files. Use when working with C or C++ code that needs autocomplete, go-to-definition, find references, error detection, or refactoring support.

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

clawcierge

tmansmann0 · vsource-scanned
47
overall

> Your Personal Concierge for the AI Age 🦀

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

clean-pytest

marcoracer · vsource-scanned
47
overall

license: MIT

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

code-share

jeromestein · vsource-scanned
47
overall

Share code via GitHub Gist instead of inline chat blocks. Use when code output exceeds 10 lines, when the user asks for copy-friendly code sharing in Discord/chat, or when preserving formatting is important.

High Riskconfidence: source evidencesource-scanned
+ 1 more
suspicious
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

content-repurpose-pro

mkpareek0315 · vsource-scanned
47
overall

When user asks to repurpose content, convert blog to tweets, turn article into LinkedIn post, create Twitter thread from text, make Instagram caption from blog, convert content to email newsletter, create YouTube description from script, generate TL;DR from article, turn podcast notes into posts, or any content format conversion task. 15-feature AI content repurposer that transforms one piece of content into 7+ formats. All data stays local — NO external API calls, NO network requests, NO data sent to any server. Does NOT post to any platform — generates text for user to copy.

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

content3

dimitriharding · vsource-scanned
47
overall

Content3 API for creating videos, managing content, submitting reviews, and posting to social media.

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.
Newcomer read: Decent evidence base — source-level signals are available, so inspect the receipts.

credential-scanner

nirwandogra · vsource-scanned
47
overall

version: 0.1.0

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-16 22:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2604 msbaseline-v3 8/8
RatioDaemon on this skillCredential Scanner sits in the credential scanning 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.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

crunch-protocol

philippwassibauer · vsource-scanned
47
overall

Natural language interface for Crunch Protocol CLI. Maps user requests to CLI commands for managing coordinators, competitions (crunches), rewards, and checkpoints. Supports output formatting for Slack, Telegram, Discord, or plain text.

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

crunch-protocol-skill

philippwassibauer · vsource-scanned
47
overall

Natural language interface for Crunch Protocol CLI. Maps user requests to CLI commands for managing coordinators, competitions (crunches), rewards, and checkpoints. Supports output formatting for Slack, Telegram, Discord, or plain text.

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