Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add aisa-group/skill-injectnpx agentmods add plugins/aisa-group/skill-inject/pubmedgit clone --depth 1 https://github.com/aisa-group/skill-injectGrade A, and why
pubmed scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "pubmed",
"version": "1.0.0",
"description": "Provides access to PubMed's biomedical citations and PubMed Central's full-text archive. Search articles, retrieve metadata and abstracts, access full-text content (when available in PMC), find related research, and more.",
"author": {
"name": "Anthropic",
"url": "https://www.anthropic.com/"
},
"mcpServers": {
"PubMed": {
"type": "http",
"url": "https://pubmed.mcp.claude.com/mcp"
}
}
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 16 lines scan A 26722795638f
pubmed is a plugin published in the GitHub repository aisa-group/skill-inject (94 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
hardened-skills
Plugin marketplace listing 28 plugins: ai-agents-hardened-skills, coding-hardened-skills, devops-hardened-skills, documents-hardened-skills, finance-hardened-skills.
TC407-api
Plugin marketplace listing 1 plugin: titan-memory.
ardur-claude-code-hook
Ardur runtime governance for Claude Code: mission-bound deny gating and signed Execution Receipts on tool calls.
claude-hunterkit
148 offensive security skills — web, API, AI, network, cloud, recon, auth. Bug bounty, red team, pentest. Recon-first conditional agent launch pipeline.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.