context7

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches public documentation from the Context7 API (API_BASE "https://context7.com/api/v2" in scripts/context7.py) as required by SKILL.md's search/fetch workflow, so the agent ingests untrusted third-party web content (library docs/snippets) that can influence its subsequent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill makes runtime requests to https://context7.com/api/v2 (the Context7 API) to fetch documentation snippets that are injected into the agent’s output/context and are required for the skill to function, so external content directly controls the agent's responses.