Haskell Ecosystem

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow includes “Fetch latest Haskell documentation” via the mcp__plugin_claude-code-home-manager_context7__query-docs Context7 integration, which at runtime can ingest outsider-authored free text from public documentation pages 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 declares a runtime tool mcp__plugin_claude-code-home-manager_context7__query-docs and usage steps that call get-library-docs with Context7 IDs (e.g. "/websites/hackage_haskell_package_optics-0_4_2_1", "/haskell-servant/servant"), which are fetched at runtime and can be injected into the agent's context to directly influence prompts/instructions.