spec-finish
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard development tools for testing, linting, and building, including
npm,pytest,cargo,mypy,ruff, andgo. These are invoked in Step 3 to validate the implementation and are expected behaviors for a software development workflow. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository during code review and validation, which represents an indirect injection surface.
- Ingestion points: Changed files and git logs are read in Step 4 and Step 5; outputs from validation tools (tests, linters) are processed in Step 3.
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded prompts within the files being reviewed.
- Capability inventory: The agent can execute arbitrary shell commands for builds and tests (Step 3) and invoke external skills like
code-reviewandcode-pull-request(Step 4 and Step 6). - Sanitization: No explicit sanitization or filtering of the repository content or tool output is described.
Audit Metadata