gsd-ship
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it is designed to process local repository content and task data to automate Pull Request creation and code reviews.\n
- Ingestion points: Local project files and task verification results.\n
- Boundary markers: The instruction file does not provide explicit delimiters or ignore-instructions for the data it processes.\n
- Capability inventory: The skill has access to tools including Bash for command execution and Write for file modifications.\n
- Sanitization: No sanitization or filtering of project content is mentioned in this wrapper.
Audit Metadata