map-design-language
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes information from multiple repository files (untrusted data) to generate or update project documentation. This creates an attack surface where malicious instructions embedded in the project's source code or manifests could influence the agent's output. \n
- Ingestion points: SKILL.md (Steps 1-3) specifies reading files such as package manifests, UI directories, CSS files, and framework theme configurations. \n
- Boundary markers: The protocol lacks explicit markers or instructions to isolate potentially adversarial content found during the research phase. \n
- Capability inventory: The skill possesses the capability to write the aggregated findings to a file within the repository (meta/DESIGN.md) as described in Step 5. \n
- Sanitization: There is no evidence of sanitization or filtering logic applied to the data before it is formatted into the final template. \n- [COMMAND_EXECUTION]: The skill performs extensive file system operations, including reading various configuration and source files and writing a new markdown file. \n
- Evidence: The protocol in SKILL.md requires systematic scanning and reading of project directories and manifests, followed by the writing of the meta/DESIGN.md file in the project's meta directory.
Audit Metadata