Rust Ecosystem

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow includes mcp__plugin_claude-code-home-manager_context7__query-docs / get-library-docs to fetch Rust documentation from external Context7 libraries (e.g., /rust-lang/book, /rust-lang/cargo.git), which is outsider-authored free text ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill issues runtime Context7 calls like get-library-docs with IDs such as "/rust-lang/book" (and other IDs like "/rust-lang/cargo.git" and "/rust-lang/rust-clippy") to fetch external documentation into the agent's context, which would be injected at runtime and can directly influence prompts and behavior.