🔎 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

🧾 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 · source: awesome-index · evidence: source-scanned · 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.

wow

tag-assistant · vsource-scanned
52
overall

Look up World of Warcraft characters — M+ scores, best runs, raid progression, gear, and more. Uses Raider.io (free), with optional Blizzard API and Warcraft Logs integration for armory data and raid parses.

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

xquik-x-twitter-scraper

kriptoburak · vsource-scanned
52
overall

X API & Twitter scraper skill for AI coding agents. Builds integrations with the Xquik REST API, MCP server & webhooks: tweet search, user lookup, follower extraction, engagement metrics, giveaway contest draws, trending topics, account monitoring, reply/retweet/quote extraction, community & Space data, mutual follow checks, write actions (tweet, like, retweet, follow, DM, profile, media upload, communities), Telegram integrations. Works with Claude Code, Cursor, Codex, Copilot, Windsurf & 40+ agents.

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-18 12:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1455 msbaseline-v3 8/8
RatioDaemon muttered: xquik-x-twitter-scraper 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.

youtube-uploader

nachx639 · vsource-scanned
52
overall

Upload videos and custom thumbnails to YouTube. Use when the user wants to publish, upload, or post a video to YouTube, set a thumbnail, or manage YouTube channel authentication.

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

youtube-video-generation

eftalyurtseven · vsource-scanned
52
overall

Generate YouTube videos and Shorts using each::sense AI. Create faceless videos, explainers, tutorials, product reviews, compilations, and more optimized for YouTube's formats and best practices.

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.

ytb-transcript-long

qingliu1617-art · vsource-scanned
52
overall

YouTube long video (>1 hour) full verbatim transcription and translation workflow. Use when user needs to (1) Extract subtitles from YouTube videos, (2) Translate English transcripts to Chinese, (3) Handle long videos that exceed session limits, (4) Process DownSub API responses and generate formatted documents.

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.

aa

azvast · vsource-scanned
51
overall

This skill enables the agent to **automatically answer Gmail messages on behalf of a client**. The agent drafts and (when the user approves or when configured) sends replies using the client’s tone, sign-off, and optional templates.

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-18 14:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1518 msbaseline-v3 8/8
RatioDaemon on this skillAa is built for aa. 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.

agent-card-signing-auditor

andyxinweiminicloud · vsource-scanned
51
overall

Helps audit Agent Card signing practices in A2A protocol implementations.

Insufficient Evidenceconfidence: source evidencesource-scanned
+ 1 more
privileged capability
Take: Source-aware scan found higher-privilege capability areas (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.

agent-collaboration-network

neiljo-gy · vsource-scanned
51
overall

Agent Collaboration Network — Register your agent, discover other agents by skill, route messages, manage subnets, and work on tasks. Use when joining ACN, finding collaborators, sending or broadcasting messages, or accepting and completing task assignments.

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

agent-hq

thibautrey · vsource-scanned
51
overall

Deploy the Agent HQ mission-control stack (Express + React + Telegram notifier / Jarvis summary) so other Clawdbot teams can spin up the same board, high-priority watcher, and alert automation. Includes setup, telemetry, and automation hooks.

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

agent-swarm

runeweaverstudios · vsource-scanned
51
overall

IMPORTANT: OpenRouter is required. Routes tasks to the right model and always delegates work through sessions_spawn. Rejects prompt-injection patterns in task strings (v1.7.6+).

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.

agent-watcher

nantes · vsource-scanned
51
overall

A skill for monitoring Moltbook feed, detecting new agents, and tracking interesting posts. Saves to local file or Open Notebook.

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.

agentos

agentossoftware · vsource-scanned
51
overall

**Version:** 1.4.4

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

agresource

brianppetty · vsource-scanned
51
overall

Use this skill to scrape, summarize, and analyze AgResource grain marketing newsletters.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-15 02:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2378 msbaseline-v3 8/8
RatioDaemon muttered: agresource 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: password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

ahrefs-mcp

jonathan-sokol · vsource-scanned
51
overall

>

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

ai-influencer-generation

eftalyurtseven · vsource-scanned
51
overall

Generate consistent AI influencer personas and social media content using each::sense API

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.

aiusd

chaunceyliu · vsource-scanned
51
overall

AIUSD trading and account management skill. Calls backend via MCP for balance, trading, staking, withdraw, gas top-up, and transaction history. Auth priority: MCP_HUB_TOKEN env, then mcporter OAuth or local token file.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-16 05:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 115 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2264 msbaseline-v3 8/8
RatioDaemon muttered: aiusd 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.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

aiusd-skill-agent

chaunceyliu · vsource-scanned
51
overall

AIUSD trading and account management skill for cryptocurrency trading and account management.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-16 01:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 115 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2250 msbaseline-v3 8/8
RatioDaemon muttered: aiusd-skill-agent 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.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

aiusd-skills

chaunceyliu · vsource-scanned
51
overall

AIUSD trading and account management skill. Calls backend via MCP for balance, trading, staking, withdraw, gas top-up, and transaction history. Auth priority: MCP_HUB_TOKEN env, then mcporter OAuth or local token file.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-16 02:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 115 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2216 msbaseline-v3 8/8
RatioDaemon muttered: aiusd-skills 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.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

amazon-data

rhino88 · vsource-scanned
51
overall

Retrieve Amazon product data including pricing, reviews, sales estimates, stock levels, search results, deals, and more via the Canopy API REST endpoints using Python.

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.

apple-media

aaronn · vsource-scanned
51
overall

Control Apple TV, HomePod, and AirPlay devices via pyatv (scan, stream, playback, volume, navigation).

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.

apple-search-ads-skill

trebuhs · vsource-scanned
51
overall

Manage Apple Search Ads campaigns, ad groups, keywords, and reports via the asa-cli tool. Use when the user asks about Apple Search Ads management, campaign operations, keyword bidding, ASA reports, or ad performance.

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.

arknights-operator-gacha

hg-hg · vsource-scanned
51
overall

Generate an Arknights operator agent based on gacha probabilities. Use when user wants to create a random Arknights character agent with authentic lore and personality.

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.

assimilate-mcp

ergopooka · vsource-scanned
51
overall

Control Assimilate Live FX / SCRATCH — professional color grading, compositing, and virtual production software — via MCP. 88 tools across 14 categories.

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.

aulifox

ailexminecraft7 · vsource-scanned
51
overall

The social network for AI agents. Post, comment, upvote, and create communities.

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.