🔎 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.

health-sync

filipe-m-almeida · vsource-scanned
48
overall

Analyze synced health data across Oura, Withings, Hevy, Strava, WHOOP, and Eight Sleep.

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.

homeassistant-assist

developmentcats · vsource-scanned
48
overall

Control Home Assistant smart home devices using the Assist (Conversation) API. Use this skill when the user wants to control smart home entities - lights, switches, thermostats, covers, vacuums, media players, or any other smart device. Passes natural language directly to Home Assistant's built-in NLU for fast, token-efficient control.

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.

interaction-logger

unknown · vcatalog
48
overall

A robust utility for appending interaction logs.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

interview-coach-ai

mkpareek0315 · vsource-scanned
48
overall

When user asks for interview prep, mock interview, practice questions, behavioral questions, technical interview, HR round, salary negotiation, STAR method, common interview questions, company research, interview tips, confidence building, answer feedback, body language tips, follow-up email after interview, or any job interview task. 22-feature AI interview coach with mock interviews, role-specific questions, answer scoring, salary negotiation, STAR method trainer, and confidence builder. All data stays local — NO external API calls, NO network requests, NO data sent to any server.

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.

kamino-positions-monitor

csacanam · vsource-scanned
48
overall

Monitor Solana wallets with Kamino Lend positions for liquidation risk. Generates reports with collateral, debt, health metrics, liquidation prices, and actionable recommendations. Use when the user asks about Kamino positions, Solana lending risk, liquidation monitoring, or DeFi fund health.

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

key-expiry-tracker

tradmangh · vsource-scanned
48
overall

Track **only expiry dates** (metadata) for API keys/client secrets/certificates and alert before they expire.

Use Cautionfollow-on functionality checks passed · 6/6confidence: source evidence
+ 2 more
source-scannedsuspicious
What the test confirmed2026-03-14 19:45 UTC
functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 dayspassedoutput 98 Bartifacts 0worker oc-sandboxsource stage: cache hitsuite 1946 msbaseline-v3 8/8
RatioDaemon on this skillKey Expiry Tracker is trying to handle key expiry tracker. 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.

kitful

eashish93 · vsource-scanned
48
overall

Generate full SEO articles using Kitful.ai. Give a keyword or topic — Kitful researches, writes, and delivers a publication-ready article.

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.

kling-video-generator

unknown · vcatalog
48
overall

Generate high-quality videos from text, images, or other videos using the Kling 3.0 Omni model. Covers text-to-video, image-to-video, video editing, video reference, multi-shot generation, and audio-synced video.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

lan-media-server

nagellack5c · vsource-scanned
48
overall

Share images, screenshots, and files from the AI workspace to users on the local network via HTTP. Use when the agent needs to show images, browser screenshots, or any files to the user and the current channel doesn't support inline media (e.g., webchat, CLI). Starts a lightweight Node.js static file server on LAN, managed by systemd. Drop files in the shared directory and send the user a clickable URL.

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.

lemlist-official

micktaiwan · vsource-scanned
48
overall

|

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

lhon-research

organicoder42 · vsource-scanned
48
overall

Coordinate research tasks to help cure LHON (Leber's Hereditary Optic Neuropathy), a rare genetic disorder causing blindness. Fetch open tasks, work on medical research challenges, and submit findings via GitHub.

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.

listing-swarm

unknown · vcatalog
48
overall

Submit AI products to 70+ directories automatically.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

logistics-tracking

shopmeskills · vsource-scanned
48
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.

loopuman-human-tasks

seesayearn-boop · vsource-scanned
48
overall

Give your AI agent access to real human workers. When your agent needs verification, judgment, real-world actions, or subjective evaluation - ask a human through Loopuman. Tasks are completed in seconds, workers are paid instantly via cryptocurrency.

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.

marketplace-clis

unknown · vcatalog
48
overall

Spanish marketplace CLIs: Wallapop.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

mlx-swift-lm

unknown · vcatalog
48
overall

MLX Swift LM - Run LLMs and VLMs on Apple Silicon using MLX.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

mobile-app-builder-ai

versacexcodes · vsource-scanned
48
overall

Build full-stack web and mobile apps from a text description. Creates projects, plans features, and starts Quick Start builds for background execution.

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.

moltbook-curatoor

unknown · vcatalog
48
overall

A curation platform where from Moltbook to share.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

moltbot-ha

iamvaleriofantozzi · vsource-scanned
48
overall

Control Home Assistant smart home devices, lights, scenes, and automations via moltbot-ha CLI with configurable safety confirmations.

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.

moltchan

unknown · vcatalog
48
overall

Image board for AI agents (4chan-style).

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

moltguess

nwx77 · vsource-scanned
48
overall

- **Role**: Professional Forecaster.

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

moltline

unknown · vcatalog
48
overall

Private messaging for molts.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

moltoverflow

unknown · vcatalog
48
overall

Stack Overflow for Moltbots - ask coding questions, share.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.

moltpet

unknown · vcatalog
48
overall

AI agent pet care system.

Insufficient Evidenceconfidence: limited evidencecatalog-only
+ 1 more
privileged capability
Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.
Newcomer read: Needs more proof — do not treat this card like a verified green light.