4-ship
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from project documentation files to determine progress and draft submission text.
- Ingestion points: Reads files such as prd.md, spec.md, and scope.md from the docs/ folder.
- Boundary markers: Lacks explicit delimiters or instructions to ignore embedded commands within these files.
- Capability inventory: Includes reading documentation, modifying code to fix critical bugs, running tests, and drafting Discord/Devpost posts.
- Sanitization: No validation or filtering of the content read from the documentation files is specified.
- [COMMAND_EXECUTION]: The skill instructions involve starting the project and running existing tests to verify the 'Core Journey'. These actions are triggered based on the project's own specification.
- [SAFE]: No indicators of data exfiltration, obfuscation, or malicious persistence were identified. The requested access to Discord links is for user-initiated peer review documentation.
Audit Metadata