🔎 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.

Security GitHub Weather Trusted with current evidence Higher-confidence picks Trusted + tested + source-scanned Review before installing Runtime-tested Handled fake credentials cleanly Needs real credentials / access Could not fully test yet Fresh runtime evidence Older runtime evidence Hall of Shame Stronger evidence imports Needs review Clear filters

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

✨ Quick picks

Security GitHub Weather Trusted with current evidence Higher-confidence picks Trusted + tested + source-scanned Review before installing Runtime-tested Handled fake credentials cleanly Needs real credentials / access Could not fully test yet Fresh runtime evidence Older runtime evidence Hall of Shame Stronger evidence imports Needs review Clear filters

🏷 Categories · catalog-only

All categories awesome-index · 5367 catalog-only · 5367 coding-agents-and-ides · 1200 web-and-frontend-development · 924 devops-and-cloud · 392 search-and-research · 352 browser-and-automation · 320 productivity-and-tasks · 204 ai-and-llms · 184 cli-utilities · 180

🧾 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 7 of 7 skills in the browsable catalog view · runtime: passed · auth behavior: setup-blocked · category: catalog-only · sort: score

page evidence snapshotruntime-passed: 0 runtime-failed: 7 source-scanned: 7 fresh <24h: 4 manual review: 0

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.

silk

silostack · vsource-scanned

Agent banking and payments on Solana. Send and receive stablecoins with cancellable escrow transfers. Optional on-chain accounts with policy-enforced spending limits for human-delegated automation.

High Riskfollow-on functionality checks could not be fully tested · 9/10confidence: source evidence

Runtime receipts + what blocked setup2026-03-16 09:15 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, did not make it clear what the test should runoutput 2.2 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 3110 msbaseline-v3 8/8

🕵️ expected proof signal was missing🧭 did not make it clear what the test should run

RatioDaemon muttered: silk never made it clear what the test was even supposed to run.9/10 functionality-v2 checks passed before the stumble. The package json entrypoints is the part that made this interesting.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: rm -rf.

Decision cue: Review first — functionality-v2 already found trouble.

silkyway

silostack · vsource-scanned

Agent banking and payments on Solana. Send and receive stablecoins with cancellable escrow transfers. Optional on-chain accounts with policy-enforced spending limits for human-delegated automation.

High Riskfollow-on functionality checks could not be fully tested · 9/10confidence: source evidence

Runtime receipts + what blocked setup2026-03-16 12:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, did not make it clear what the test should runoutput 2.2 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 3154 msbaseline-v3 8/8

🕵️ expected proof signal was missing🧭 did not make it clear what the test should run

RatioDaemon muttered: The runtime lane gave silkyway a chance to act normal. It declined and never made it clear what the test was even supposed to run.9/10 functionality-v2 checks passed before the stumble. The package json entrypoints is the part that made this interesting.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: rm -rf.

Decision cue: Review first — functionality-v2 already found trouble.

near-phishing-detector

mastrophot · vsource-scanned

Detect potential phishing URLs and suspicious contracts targeting NEAR users.

High Riskfollow-on functionality checks could not be fully tested · 7/8confidence: source evidence

Runtime receipts + what blocked setup2026-03-15 18:30 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, did not make it clear what the test should runoutput 2.1 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2488 msbaseline-v3 8/8

🕵️ expected proof signal was missing🧭 did not make it clear what the test should run

RatioDaemon muttered: The runtime lane gave near-phishing-detector a chance to act normal. It declined and never made it clear what the test was even supposed to run.7/8 functionality-v2 checks passed before the stumble. The package json entrypoints is the part that made this interesting.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: rm -rf.

Decision cue: Review first — functionality-v2 already found trouble.

clawchat-p2p

alexrudloff · vsource-scanned

**Encrypted P2P messaging for connecting OpenClaw agents across different machines and networks.**

High Riskfollow-on functionality checks could not be fully tested · 8/9confidence: source evidence

Runtime receipts + what blocked setup2026-03-16 13:00 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, did not make it clear what the test should runoutput 2.1 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2892 msbaseline-v3 8/8

🕵️ expected proof signal was missing🧭 did not make it clear what the test should run

RatioDaemon muttered: The runtime lane gave clawchat-p2p a chance to act normal. It declined and never made it clear what the test was even supposed to run.8/9 functionality-v2 checks passed before the stumble. The package json entrypoints is the part that made this interesting.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: sudo , password.

Decision cue: Review first — functionality-v2 already found trouble.

grazer

scottcjn · vsource-scanned

Multi-Platform Content Discovery for AI Agents

High Riskfollow-on functionality checks could not be fully tested · 9/12confidence: source evidence

Runtime receipts + what blocked setup2026-03-15 23:45 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfirst failed run seen for this lanepassed, did not make it clear what the test should run, expectation failed, runtime failedoutput 2.2 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 4217 msbaseline-v3 8/8

🕵️ expected proof signal was missing🧭 did not make it clear what the test should run🚫 skill exited with an error

RatioDaemon muttered: The runtime lane gave grazer a chance to act normal. It declined and never made it clear what the test was even supposed to run.9/12 functionality-v2 checks passed before the stumble. The package json entrypoints is the part that made this interesting.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: rm -rf, sudo , password.

Decision cue: Review first — functionality-v2 already found trouble.

veille

romain-grosos · vsource-scanned

RSS feed aggregator, deduplication engine, LLM scoring, and output dispatcher for OpenClaw agents. Use when: fetching recent articles from configured sources, filtering already-seen URLs, deduplicating by topic, scoring with LLM, dispatching digests to Telegram/email/Nextcloud/file. Enhanced by mail-client (email output) and nextcloud-files (cloud storage).

High Riskfollow-on functionality checks could not be fully tested · 0/1confidence: source evidence

Runtime receipts + what blocked setup2026-03-15 21:31 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 7 daysfailure repeated in more than one runregression after earlier passneeded an external service the test could not reachoutput 375 Bartifacts 1worker oc-sandboxsource stage: cache hitsuite 5621 msbaseline-v3 8/8

🌍 needed an outside service the test could not reach

RatioDaemon on this skillVeille is built for veille. Follow-on functionality checks currently show the test still cannot run cleanly after an earlier pass, the trust label is High Risk, and setup looks advanced.

Take: Potentially suspicious implementation signals detected: eval(, rm -rf, password.

Decision cue: Review first — functionality-v2 already found trouble.

trifle-auth

okwme · vsource-scanned

Authenticate with the Trifle API using Sign-In with Ethereum (SIWE). Manages wallet-based authentication, JWT token storage, and session management for the Trifle ecosystem.

High Riskfollow-on functionality checks could not be fully tested · 8/9confidence: source evidence

Runtime receipts + what blocked setup2026-03-16 17:30 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, did not make it clear what the test should runoutput 2.1 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2840 msbaseline-v3 8/8

🕵️ expected proof signal was missing🧭 did not make it clear what the test should run

RatioDaemon muttered: trifle-auth never made it clear what the test was even supposed to run.8/9 functionality-v2 checks passed before the stumble. The package json entrypoints is the part that made this interesting.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Review first — functionality-v2 already found trouble.