fancy-ship
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
git rev-parse HEADcommand to retrieve and record a commit hash for rollback documentation during the release process (SKILL.md). - [INDIRECT_PROMPT_INJECTION]: The skill interacts with local project files to maintain state, creating a surface for potential instruction injection if these files are manipulated.
- Ingestion points: The agent reads from files in the
memory/directory, such asPROGRESS.md,FAILURES.md, andDECISIONS.md(SKILL.md). - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these files.
- Capability inventory: The skill is permitted to write to local repository files and execute basic shell commands for version control.
- Sanitization: The skill does not define methods for sanitizing or validating the content of the memory files before they are processed.
Audit Metadata