docs-seeker

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

• Third-party content exposure detected (low risk: 0.10). The agent skill fetches documentation from context7.com and GitHub repositories selected via user queries and URLs, representing external content retrieval where an attacker could publish poison.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains operational code that fetches documentation and queries configuration from context7.com, which is an unverified third-party service lacking established first-party provenance or cryptographic verification.