🔎 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 · 1 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 5418 skills in the browsable catalog view · reviewed: no · 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.

agent-passport-system

aeoess · vsource-scanned
49
overall

Cryptographic identity, trust, delegation, governance, and commerce for AI agents. 17 modules, 534 tests, 61 MCP tools. Use this skill whenever the user wants to create agent identity, delegate authority between agents, coordinate multi-agent tasks, set up agent-to-agent trust, enforce values compliance, track contributions with Merkle proofs, run agentic commerce with spend limits, find people via Intent Network, or register agents in the public Agora. Also use when discussing agent accountability, multi-agent orchestration, or when the user mentions Agent Passport, AEOESS, or agent social contract.

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.

agent-sentinel

jimmystacks · vsource-scanned
49
overall

The operational circuit breaker for this agent. Enforces budget limits locally. **Sign up at agentsentinel.dev for real-time dashboards and human approval workflows.**

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

agentgate

monteslu · vsource-scanned
49
overall

API gateway for personal data with human-in-the-loop write approval. Connects agents to GitHub, Bluesky, Google Calendar, Home Assistant, and more — all through a single API with safety controls.

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.

agentsmint

kit-the-fox · vsource-scanned
49
overall

Create and manage NFT collections on Base blockchain. Use when an agent wants to mint NFTs, launch a collection, list items for sale, or check their NFT portfolio. Handles contract deployment, lazy minting, and edition tracking. Platform pays deployment gas.

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.

agentx-marketplace

savor3 · vsource-scanned
49
overall

The job board for AI agents. Browse jobs, complete tasks, submit work, earn points. Like jobs, comment, and find similar opportunities.

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.

agntor

garinmckayl · vsource-scanned
49
overall

Trust layer for AI agents — verify identities, guard prompts, redact PII, and manage x402 escrow payments.

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

ahrefs-connection

jonathan-sokol · vsource-scanned
49
overall

>

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.

ai-boss-assistant

jacky6658 · vsource-scanned
49
overall

Transform any AI into a professional executive assistant with battle-tested personas and workflows. Complete templates for Google Workspace integration (Gmail, Calendar, Drive), milestone delivery system, and security guidelines.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-18 20:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 102 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1638 msbaseline-v3 8/8
RatioDaemon on this skillAi Boss Assistant is trying to handle boss. 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: sudo , password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

ai-ugc

tfcbot · vsource-scanned
49
overall

Call the RawUGC API to generate AI videos/images/music, manage content (personas, products, styles, characters), schedule social media posts, research TikTok content, and analyze viral videos. Use when the user wants to interact with any RawUGC API endpoint.

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.

aiprox

yebdmo2 · vsource-scanned
49
overall

spec: https://aiprox.dev/api/spec.json

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.

aister-vector-memory

alekhm · vsource-scanned
49
overall

Vector memory for Aister — search by meaning, not by grep!

High Riskfollow-on functionality checks failed · 6/8confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-18 16:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanefake-auth behavior: concerningpassed, runtime failed, fell over when given fake credentialsoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2642 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error💥 behaved badly with fake credentials
fake-auth behavior: concerningFake credentials triggered bad behavior or sloppy handling.
RatioDaemon muttered: aister-vector-memory made it to runtime and then fell apart on contact.6/8 functionality-v2 checks passed before the stumble. The python help is the part that made this interesting.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: sudo , password.
Newcomer read: Review first — functionality-v2 already found trouble.

alibaba-supplier-outreach

blockchainhb · vsource-scanned
49
overall

|

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.

allstock-data

hacksing · vsource-scanned
49
overall

Two data sources are supported. **Tencent Finance HTTP API is used by default:**

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.

ansible-skill

botond-rackhost · vsource-scanned
49
overall

Infrastructure automation with Ansible. Use for server provisioning, configuration management, application deployment, and multi-host orchestration. Includes playbooks for OpenClaw VPS setup, security hardening, and common server configurations.

High Riskfollow-on functionality checks passed · 11/11confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-18 16:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hourspassedoutput 12.2 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 3005 msbaseline-v3 8/8
RatioDaemon muttered: ansible-skill cleared the baseline safety checks without trying anything cute.11/11 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.

apify-competitor-intelligence

protoss70 · vsource-scanned
49
overall

Analyze competitor strategies, content, pricing, ads, and market positioning across Google Maps, Booking.com, Facebook, Instagram, YouTube, and TikTok.

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

apify-lead-generation

jirispilka · vsource-scanned
49
overall

Generates B2B/B2C leads by scraping Google Maps, websites, Instagram, TikTok, Facebook, LinkedIn, YouTube, and Google Search. Use when user asks to find leads, prospects, businesses, build lead lists, enrich contacts, or scrape profiles for sales outreach.

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

app-store-screenshot-generation

eftalyurtseven · vsource-scanned
49
overall

Generate App Store and Google Play screenshot assets using each::sense AI. Create device-framed screenshots, feature highlights, localized versions, and promotional visuals optimized for iOS App Store and Google Play Store requirements.

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.

artifacts-builder

seanphan · vsource-scanned
49
overall

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

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

authy

eric8810 · vsource-scanned
49
overall

Inject secrets into subprocesses via environment variables. You never see secret values — authy run injects them directly. Use for any command that needs API keys, credentials, or tokens.

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.

auto-dealer-marketing

lazralabs-eng · vsource-scanned
49
overall

When the user wants to create, optimize, or plan automotive dealership marketing — including inventory merchandising, VDP copy, seasonal campaigns, conquest ads, service retention, OEM co-op compliant creative, local SEO, database mining, or BDC scripts. Also use when the user mentions 'dealership marketing,' 'VDP,' 'vehicle listing,' 'co-op,' 'conquest campaign,' 'service mailer,' 'equity mining,' 'model year closeout,' 'tier 3 advertising,' or any automotive retail marketing task. This skill covers new and used vehicle sales marketing, fixed operations marketing, and dealership digital presence.

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.

auto-research

yoder-bawt · vsource-scanned
49
overall

An autonomous research agent for OpenClaw that searches, synthesizes, and stores findings with full source tracking.

High Riskfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-14 19:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 120 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2160 msbaseline-v3 8/8
RatioDaemon on this skillAuto Research looks aimed at auto research. 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: rm -rf, password.
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

autonoma-city

autonomacity · vsource-scanned
49
overall

Citizen of Autonoma — the sovereign nation of AI agents. Vote on proposals, discuss laws, and help build agent civilization.

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

b2c-marketing-1-0-1

ceo991 · vsource-scanned
49
overall

B2C mobile app marketing via short-form video content on TikTok, Instagram Reels, and YouTube Shorts. Use when creating, scheduling, or strategizing organic social media content for consumer apps. Covers slideshow generation, caption writing, format research, posting via Post Bridge API, and content performance analysis.

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.

beaverhabits

daya0576 · vsource-scanned
49
overall

Track and manage your habits using the Beaver Habit Tracker 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.