diataxis
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
git logto inspect the history of documentation files. This is used to determine if files have been intentionally reclassified in the past. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes documentation files from the project environment to categorize them.
- Ingestion points: Reads project files such as
README.md,CONTRIBUTING.md, and content within thedocs/directory. - Boundary markers: The instructions do not define clear delimiters or warnings for the agent to ignore instructions embedded within the documentation it is analyzing.
- Capability inventory: The agent has the ability to execute git commands, move/rename files, and write new documentation content based on its analysis.
- Sanitization: No sanitization or validation of the ingested file content is performed before processing.
Audit Metadata