context7

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

• Third-party content exposure detected (high risk: 0.90). The skill's helper script (scripts/context7.sh) and SKILL.md explicitly fetch public library docs and code examples via curl to the Context7 API (default https://context7.com/api/v2) and instruct the agent to read and act on those results (search/docs/json), exposing it to untrusted third‑party content that can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime shell helper calls the external API at https://context7.com/api/v2 (e.g., via curl to ${base_url}/context and /libs/search) to fetch documentation and code examples which are then injected into agent context and can directly control prompts/output.