Radar / AI security / PlugVet
PlugVet
An independent public directory that grades AI agent skills, plugins, and MCP servers with evidence-backed hygiene grades (A-F).
Why it matters
A trust layer for the agent-plugin supply chain: it reads the source, runs 8 hygiene checks (permissions, install/update steps, network, secrets, agent instructions, obfuscation, licence, maintainer activity), and publishes a public letter grade with the evidence and grading date. 11,739 entries graded at launch across Claude Code skills, Cursor plugins, Codex plugins, and MCP servers; grades are explicitly a hygiene screen, not a security guarantee.
What you could build with it
A package-registry or marketplace team could embed the same evidence-backed hygiene grading into its listing pages: every submitted agent skill or plugin gets an automatic permissions-and-network check, with the public grade shown next to the install button, so developers see supply-chain risk before they click install.
Does it hold up?
Too early to judge — launched hours ago, and the on-demand repo scanner is not yet connected, so independent evidence of real-world use beyond the 11,739 pre-graded directory entries is not available.
Built with PlugVet
- Show HN: PlugVet, hygiene grades for AI agent plugins with the evidence shownHacker News (via WeSearch feed record) · Launch post for PlugVet on Hacker News, published 23 Oct 2026 13:28 UTC (18:58 IST), linking to plugvet.com. 8 hygiene checks, 11,739 entries graded at launch.
Learn more
First spotted on article: source.
More AI security
iFixAi: independent auditing of AI agentsIndependent AI-agent auditor: 250+ inspections across 69 misalignment categories (red teaming + operational assurance)…security · JEV 0.76Cloudflare security-audit-skill: six-phase agent-driven security audits with independently verified findingsOpen-source MIT coding-agent skill that runs a codebase through six audit phases — reconnaissance, coverage-led…security · JEV 0.74OpenAI, Anthropic and Google DeepMind jointly unveil cyber-focused safety models and safeguardsThe three rival labs disclosed weeks of behind-the-scenes coordination and jointly released a set of cyber-focused AI…security · JEV 0.73OpenAI textGrain watermarking for ChatGPT and Codex in the EUOpenAI will roll out its invisible textGrain watermarking system to ChatGPT/Codex users in the EU over the coming…security · JEV 0.65Cloudflare security-audit-skill: multi-phase security audits for coding agentsA coding-agent skill that runs multi-phase security audits with independently verified, machine-checkable findings.security · JEV 0.63LiveNerf: a pre-registered benchmark for post-release model driftOpen-source, pre-registered 30-day benchmark that detects whether Claude Opus 5.5 quietly gets worse after launch.security · JEV 0.61
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.