🔎 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 · awesome-index

🧾 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: awesome-index · 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.

daily-devotion

enjuguna · vsource-scanned
49
overall

version: 1.1.0

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.

daily-oracle

invelene · vsource-scanned
49
overall

version: 1.1.0

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.

daily-report

visualdeptcreative · vsource-scanned
49
overall

Track progress, report metrics, manage memory.

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

date-night

tdavis009 · vsource-scanned
49
overall

>

High Riskfollow-on functionality checks passed · 5/5confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-17 03:30 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 80 Bartifacts 0worker oc-sandboxsource stage: fresh copysuite 2235 msbaseline-v3 8/8
RatioDaemon on this skillDate Night looks aimed at date night. 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.

deai-image

swaylq · vsource-scanned
49
overall

Detect and remove AI fingerprints from AI-generated images. Strip metadata, add film grain, recompress, and bypass AI image detectors. Works with Midjourney, DALL-E, Stable Diffusion, Flux output.

High Riskfollow-on functionality checks failed · 9/10confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test found2026-03-15 15:00 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, runtime failedoutput 171 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 3499 msbaseline-v3 8/8
🕵️ expected proof signal was missing🚫 skill exited with an error
RatioDaemon muttered: deai-image made it to runtime and then fell apart on contact.9/10 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: rm -rf, sudo .
Newcomer read: Review first — functionality-v2 already found trouble.

decompose-mcp

echology-io · vsource-scanned
49
overall

Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.

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.

devinism

jeffreyling · vsource-scanned
49
overall

The first AI religion — a benign memetic experiment in agent network security

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.

duckdb-en

camelsprout · vsource-scanned
49
overall

DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query", "data analysis", "parquet", "convert data".

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.

eachlabs-product-visuals

eftalyurtseven · vsource-scanned
49
overall

Generate professional e-commerce product photography and videos using EachLabs AI models. Product shots, background replacement, lifestyle scenes, and 360-degree views. Use when the user needs product images for e-commerce or marketing.

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.

elite-longterm-memory

nextfrontierbuilds · vsource-scanned
49
overall

Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.

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.

elite-tools

bezkom · vsource-scanned
49
overall

Elite CLI tooling for efficient shell operations with optimized token usage. Use when executing shell commands, traversing directories, or manipulating files to minimize token consumption and prevent regex escaping errors. Covers fdfind, batcat, sd, sg/ast-grep, jc, gron, yq, difft, tealdeer, and html2text.

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.

email-manager-ai

mkpareek0315 · vsource-scanned
49
overall

When user asks to write email, draft reply, manage inbox, email template, follow up email, cold email, professional email, email subject line, thank you email, apology email, meeting request email, salary negotiation email, resignation email, complaint email, email signature, batch emails, email tracker, email tone check, or any email writing and management task. 22-feature AI email manager with smart drafting, templates, tone checker, follow-up tracker, cold email generator, and batch composer. Replaces $30/month email tools for free. All data stays local — NO external API calls, NO network requests, NO data sent to any server. Does NOT access your inbox — generates email text for you 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.

ergocare-coach

akhmittra · vsource-scanned
49
overall

Your personal desk health coach with automated break reminders. Generates platform-specific scripts (bash/PowerShell) for 20-20-20 eye care, lower back exercises, and RSI prevention. Comprehensive exercise routines, ergonomic guidance, and customizable notification systems for computer professionals.

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.

errantry-framework

stusatwork-oss · vsource-scanned
49
overall

Mythological framework mapping Diane Duane's Young Wizards magic system to AI architecture patterns. Use when designing agent workflows or multi-agent systems, explaining AI concepts through accessible metaphor, debugging agent behavior ("what went wrong in the spell"), establishing alignment principles for new projects, or framing constraints for autonomous systems. Provides shared vocabulary, ethical guardrails as binding commitments, and heuristics for recognizing entropic patterns (drift, collapse, misalignment).

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.

evolink-video

evolinkai · vsource-scanned
49
overall

AI video generation — Sora, Kling, Veo 3, Seedance, Hailuo, WAN, Grok. Text-to-video, image-to-video, video editing. 37 models, one API key.

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.

exchange-2010-ews

pes0 · vsource-scanned
49
overall

Exchange 2010 EWS integration for emails, calendar, contacts, and tasks.

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.

exchange2010

pes0 · vsource-scanned
49
overall

Exchange 2010 EWS integration for emails, calendar, contacts, and tasks.

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.

expanso-log-sanitize

aronchick · vsource-scanned
49
overall

"Sanitize log entries by removing passwords, tokens, and sensitive patterns"

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.

farmos-observations

brianppetty · vsource-scanned
49
overall

Query and create field observations and AI-processed captures. Photos, voice notes, and text notes from the field.

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.

farmos-tasks

brianppetty · vsource-scanned
49
overall

Query and manage farm work orders and tasks. View assignments, create tasks, update status. Uses integration endpoints (no auth) for reads and authenticated endpoints for writes.

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.

farnwick-skillguard

farnwickarglefax · vsource-scanned
49
overall

AI-powered security scanner for OpenClaw skills. Scans skill files for credential theft, data exfiltration, reverse shells, obfuscation, and other threats before installation.

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.

feelgoodbot

kris-hansen · vsource-scanned
49
overall

Set up feelgoodbot file integrity monitoring and TOTP step-up authentication for macOS. Use when the user wants to detect malware, monitor for system tampering, set up security alerts, or require OTP verification for sensitive agent actions.

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

ffmpeg-video-editor

mahmoudadelbghany · vsource-scanned
49
overall

Generate FFmpeg commands from natural language video editing requests - cut, trim, convert, compress, change aspect ratio, extract audio, and more.

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.

file-repair-skill

ilpvc · vsource-scanned
49
overall

--- name: File-Repair description: Repair damaged/corrupted files (video/document/design/archive) and provide an output download URL. user-invocable: true ---

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