context7-auto-research

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls the context7-fetcher sub-skill via the Task tool to fetch documentation from the external Context7 API (node scripts/context7-api.cjs context ...), and that fetched documentation content is then ingested into the agent’s LLM context for answering (outsider-authored public/third-party documentation).

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

• Potentially malicious external URL detected (high risk: 0.85). The skill runs the included script at runtime which calls the Context7 API (https://context7.com/api/v2) to fetch documentation that is injected into the agent's responses, so external content from that URL directly controls the agent's output.