moai-context7-lang-integration

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to call Context7 APIs (resolve_library_id and get_library_docs) to fetch public library documentation from Context7 (e.g., context7.io), which the agent ingests and uses in workflows to inform actions and generate outputs, thus exposing it to untrusted third‑party content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill relies on runtime calls to Context7 to fetch Markdown documentation (e.g. https://context7.io or https://context7.io/libraries) via get_library_docs, and that fetched content is injected into the agent's context and can directly control prompts, making it a required external dependency.