context7

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

• Third-party content exposure detected (low risk: 0.10). The required workflow queries the Context7 API for library documentation based on search terms, which involves retrieving and processing third-party library reference content from an external source.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to make runtime HTTP queries to context7.com via curl to fetch documentation and API instructions that govern agent behavior, but lacks established official provenance or integrity verification for that third-party domain.