context7

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches external, public library documentation via Context7 (see SKILL.md "Lane A: Docs lookup" using ctx7 library / ctx7 docs and the backup scripts/context7.py which calls https://context7.com/api/v2), and it requires the agent to read and use that retrieved docs content to produce actionable guidance/commands—so untrusted third‑party doc content can materially influence agent decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill runs scripts/context7.py at runtime (e.g., via "op run --env-file ... -- python3 scripts/context7.py") which makes HTTPS requests to https://context7.com/api/v2 (and api.context7.com) to fetch documentation that is injected into the agent's context and therefore directly controls prompts/instructions.