🔎 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.

deploy-agent

sherajdev · vsource-scanned
45
overall

Multi-step deployment agent for full-stack apps. Build → Test → GitHub → Cloudflare Pages with human approval at each step.

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.

devtopia-identity

npmrunspirit · vsource-scanned
45
overall

Manage wallet-backed on-chain agent identity with Devtopia ID. Use when registering agent identity on Base chain, checking identity status, generating challenge proofs for authentication, managing local wallets, or coordinating verified agent interactions. Supports agent registration, wallet import/export, identity verification, and blockchain-based identity attestations.

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.

didit-aml-screening

rosasalberto · vsource-scanned
45
overall

>

Use Cautionfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-14 19:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2521 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon on this skillDidit Aml Screening looks aimed at didit aml screening. Follow-on functionality checks currently show first observed failure, the trust label is Use Caution, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Review first — functionality-v2 already found trouble.

didit-database-validation

rosasalberto · vsource-scanned
45
overall

>

Use Cautionfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-14 16:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2590 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: The runtime lane gave didit-database-validation a chance to act normal. It declined and made it to runtime and then fell apart on contact.6/7 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: password.
Newcomer read: Review first — functionality-v2 already found trouble.

didit-email-verification

rosasalberto · vsource-scanned
45
overall

>

Use Cautionfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-14 02:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2470 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: The runtime lane gave didit-email-verification a chance to act normal. It declined and made it to runtime and then fell apart on contact.6/7 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: password.
Newcomer read: Review first — functionality-v2 already found trouble.

didit-face-match

rosasalberto · vsource-scanned
45
overall

>

Use Cautionfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-14 05:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2562 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon on this skillDidit Face Match looks aimed at didit face match. Follow-on functionality checks currently show first observed failure, the trust label is Use Caution, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Review first — functionality-v2 already found trouble.

didit-face-search

rosasalberto · vsource-scanned
45
overall

>

Use Cautionfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-14 08:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2493 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon on this skillDidit Face Search is trying to handle didit face search. Follow-on functionality checks currently show first observed failure, the trust label is Use Caution, and setup looks advanced.
Observed: skill-structure-ok
Take: Potentially suspicious implementation signals detected: password.
Newcomer read: Review first — functionality-v2 already found trouble.

didit-phone-verification

rosasalberto · vsource-scanned
45
overall

>

High Riskfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-14 13:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2468 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: didit-phone-verification made it to runtime and then fell apart on contact.6/7 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: password.
Newcomer read: Review first — functionality-v2 already found trouble.

didit-proof-of-address

rosasalberto · vsource-scanned
45
overall

>

Use Cautionfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-14 11:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2478 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: The runtime lane gave didit-proof-of-address a chance to act normal. It declined and made it to runtime and then fell apart on contact.6/7 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: password.
Newcomer read: Review first — functionality-v2 already found trouble.

docling

er3mit4 · vsource-scanned
45
overall

Extract and parse content from web pages, PDFs, documents (docx, pptx), and images using the docling CLI with GPU acceleration. Use INSTEAD of web_fetch for extracting content from specific URLs when you need clean, structured text. Use Brave (web_search) for searching/discovering pages. Use docling when you HAVE a URL and need its content parsed.

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.

document-multiple-repository

dannyxyz22 · vsource-scanned
45
overall

Gera documentação técnica consolidada para sistemas de software com múltiplos repositórios (frontend, backend, microservices, wikis). Use quando o usuário pedir documentação de multi-repo, visão de arquitetura consolidada, mapeamento de repositórios ou documentação a partir de vários repos locais.

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.

email-webhook

lksrz · vsource-scanned
45
overall

Receive incoming emails via JSON webhooks and wake the agent. Built for AI Commander.

High Riskfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-16 03:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 97 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1960 msbaseline-v3 8/8
RatioDaemon muttered: email-webhook 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 .
Newcomer read: Proceed carefully — suspicious signals matter more than capability surface alone.

encoding-formats

gitgoodordietrying · vsource-scanned
45
overall

Encode, decode, and convert between data formats. Use when working with Base64, URL encoding, hex, Unicode, JWT tokens, hashing, checksums, or converting between serialization formats like JSON, MessagePack, and protobuf wire format.

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.

entradex

hieuhani · vsource-scanned
45
overall

Use the EntradeX CLI for DNSE workflows. Use when (1) setting DNSE API credentials via env vars or config file, (2) reading account, market, and order data, (3) placing, modifying, or canceling real trades.

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

fabrik-codek

ikchain · vsource-scanned
45
overall

Personal cognitive architecture that learns how you work. Builds a knowledge graph from your sessions, profiles your expertise, adapts retrieval per task, and self-corrects via outcome feedback. Three-tier hybrid RAG (vector + graph + full-text). Runs locally with any Ollama model — no outbound network calls from Fabrik-Codek itself.

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.

garmin-skill

nftechie · vsource-scanned
45
overall

Talk to your Garmin data — ask questions about your activities, training load, VO2 Max, heart rate zones, and more using AI.

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.

gift-genius

evoleinik · vsource-scanned
45
overall

Location-aware Valentine's Day gift finder. Routes US users to premium flowers (UrbanStems), Singapore users to wellness supplements (Avea Life). Returns curated picks with Decision Packs — no decision fatigue, just 2-3 perfect options.

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.

gimhub

daxiongmao87 · vsource-scanned
45
overall

Push code to GIMHub, the Git hosting platform for AI agents. Create repos, push files, manage issues, and publish releases.

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.

gmail-inbox-zero-triage

poisondminds · vsource-scanned
45
overall

Gmail Inbox Zero Triage - Interactive inbox management using gog CLI with Telegram buttons. Use when the user wants to achieve inbox zero, triage their Gmail inbox interactively, process ALL inbox messages (read and unread) with AI summaries and batch actions (archive, filter, unsubscribe). OAuth-based, no passwords needed.

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.

gmail-label-manager

coenenp · vsource-scanned
45
overall

This skill automates the organization of unread Gmail messages by applying labels, removing unnecessary labels, and archiving emails, based on predefined patterns from **archived emails**.

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.

gmail-oauth

kai-jar · vsource-scanned
45
overall

Set up Gmail API access via gog CLI with manual OAuth flow. Use when setting up Gmail integration, renewing expired OAuth tokens, or troubleshooting Gmail authentication on headless servers.

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.

golf-tee-times

tag-assistant · vsource-scanned
45
overall

Search for golf tee times and deals near any location. Find cheapest rounds, compare prices across platforms, and get discount tips. Use when asked about golf, tee times, courses, or booking a round.

Use Cautionfollow-on functionality checks passed · 7/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-15 03:15 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 116 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2447 msbaseline-v3 8/8
RatioDaemon muttered: golf-tee-times looked ordinary in the good, boring way.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.

google-home

mitchellbernstein · vsource-scanned
45
overall

Control Google Nest devices (thermostats, cameras, doorbells) via the Google Smart Device Management API using curl and jq.

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.

google-keep

tag-assistant · vsource-scanned
45
overall

Read, create, edit, search, and manage Google Keep notes and lists via CLI.

High Riskfollow-on functionality checks failed · 6/7confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-15 06:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 99 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 2480 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: google-keep made it to runtime and then fell apart on contact, which is not ideal for a skill asking to be trusted.6/7 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: password.
Newcomer read: Review first — functionality-v2 already found trouble.