context7

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly calls the Context7 API (https://context7.com/api/v2) from scripts/context7.py and the SKILL.md workflow to fetch public library documentation that the agent is instructed to read and use to guide implementations, so untrusted third‑party content can influence agent decisions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime script makes authenticated requests to the Context7 API (https://context7.com/api/v2, e.g. /context and /libs/search) to fetch documentation text that is intended to be injected into the agent's context/prompts, so external content directly controls prompts at runtime.