hoja-de-ruta
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically
git log --all --reverse --format="%H %aI %s %b"andgit status, to extract project history and status information. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including project documentation (PRD.md, SPECS.md) and git commit messages.
- Ingestion points: The agent reads the full content of documentation files (
PRD.md,SPECS.md) and the body of git commit messages viagit log. - Boundary markers: The skill does not specify any delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the git history or project files.
- Capability inventory: The skill allows the agent to read local files, execute git commands, and write/modify Markdown files within the project directory.
- Sanitization: No sanitization or validation logic is defined to prevent instructions found in commit messages from being interpreted as agent commands.
Audit Metadata