agents-market-installer

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow runs agents-market search <query> --json and agents-market apply ... --json (and optionally registry info --registry <source> --json) which can fetch and ingest outsider-provided registry/packs content based on user-supplied inputs, exposing indirect prompt injection via that consumed text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill tells users to run "npx github:tt-a1i/agents-market#preview-0.1.0", which will fetch and execute remote code from that GitHub repo at runtime (remote package execution), so it is a runtime external dependency that executes code.