charted-green
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes external design documents and test files, creating a surface for indirect prompt injection where instructions could be hidden in those files.
- Ingestion points: designDocPath and testFilePath.
- Boundary markers: No delimiters or ignore instructions are present for the ingested files.
- Capability inventory: The skill can update local code and execute tests via the Wallaby MCP server.
- Sanitization: The skill does not perform validation or sanitization of the file contents.
- Command Execution (SAFE): The skill uses the Wallaby MCP server to verify test results. This is the primary intended function of the skill and is triggered in the user's local development context.
Audit Metadata