🔎 Evidence browser

Search the skill radar

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 only Higher-confidence picks Lower-friction local candidates Review-first installs Sandbox-tested Fresh runtime Stale runtime 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

🏷 Categories · ai-and-llms

🧾 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.

📏 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.

Results

Showing 8 of 8 results for “security” · category: ai-and-llms · sort: relevance

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

aegis-security

swiftadviser · vsource-scanned

overall

Blockchain security API for AI agents. Scan tokens, simulate transactions, check addresses for threats.

High Riskconfidence: source evidencesource-scanned

+ 1 more

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

arc-security-mcp

trypto1019 · vsource-scanned

overall

AI-first security intelligence with LLM-powered intent analysis. 743+ findings from 361+ skill audits, 25 pattern rules, 22 attack classes.

Insufficient Evidenceconfidence: source evidencesource-scanned

+ 1 more

Take: Source-aware scan found normal operational surface via environment, network, or shell-related references.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

bunni-modes

dubhorizoned · vcatalog

overall

A persona and model-switching toolkit featuring Bunni, your bubbly cyber-security assistant.

Insufficient Evidenceconfidence: limited evidencecatalog-only

+ 1 more

Take: Indexed from the community catalog. Source-aware static analysis and manual review are still pending.

Decision cue: Thin evidence slice — do not treat this card like a verified green light.

anti-injection-skill

georges91560 · vsource-scanned

overall

Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.

High Riskconfidence: source evidencesource-scanned

+ 1 more

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

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

pincer

panzacoder · vsource-scanned

overall

Security-first wrapper for installing agent skills. Scans for malware, prompt injection, and suspicious patterns before installation. Use instead of `clawhub install` for safer skill management.

High Riskconfidence: source evidencesource-scanned

+ 1 more

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

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

lieutenant

jd-delatorre · vsource-scanned

overall

AI agent security and trust verification. Scan messages, agent cards, and A2A communications for prompt injection, jailbreaks, and malicious patterns. Use when protecting agents from attacks, verifying external agents, or scanning untrusted content.

Use Cautionconfidence: source evidencesource-scanned

+ 1 more

Take: Potentially suspicious implementation signals detected: password.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

argus

sooyoon-eth · vsource-scanned

overall

Blockchain intelligence & AI security. Token analysis, address risk, smart money tracking, AML compliance, and prompt injection detection. Free tier (3/day, 1-min cooldown). Pay-per-query via x402 or Stripe credits.

Insufficient Evidenceconfidence: source evidencesource-scanned

+ 1 more

Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

agent-linguo

xiwan · vsource-scanned

overall

Efficient Agent Communication Protocol Language. Unreadable by humans, instantly understood by Agents. Saves 70%+ tokens, structured, extensible. Supports capability declaration, security level negotiation, and end-to-end encryption. Trigger words: 👽语, alien language, agent lingua, translate 👽语, encode lingua. Also triggered when user sends messages starting with 👽.

Insufficient Evidenceconfidence: source evidencesource-scanned

+ 1 more

Take: Source-aware scan found higher-privilege capability areas (token), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.