skill-host-compat
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of a local script,
scripts/ci/validate-skill-host-compat.js, to perform linting and validation of the skill repository. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data (other skill files), creating a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The skill reads file content and directory metadata from
skills/,.agents/skills/, and.cursor/skills/. - Boundary markers: No specific boundary markers are documented to protect the agent from interpreting instructions found within the analyzed files.
- Capability inventory: The skill environment supports script execution using Node.js.
- Sanitization: There is no mention of input sanitization or filtering for the content processed by the linter.
Audit Metadata