ai-research-skills

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly tells the agent to read and follow instructions from a public URL (see scripts/setup-claude.sh Option C: "Read https://www.orchestra-research.com/ai-research-skills/welcome.md"), which requires fetching untrusted third-party web content that the agent is expected to interpret and which could materially change its actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The installer and scripts call npx @orchestra-research/ai-research-skills (npm package https://www.npmjs.com/package/@orchestra-research/ai-research-skills), which at runtime fetches and executes remote package code and is relied upon by the skill installation, so it can directly execute remote code on install.