gsd-docs-update
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate documentation tasks using authorized tools. The file access and command execution patterns observed are consistent with its stated purpose.
- [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill ingests untrusted codebase data during the documentation process. \n
- Ingestion points: Project codebase files are read using the Read, Glob, and Grep tools. \n
- Boundary markers: There are no explicit instructions to the agent to disregard instructions found within the codebase files. \n
- Capability inventory: The skill utilizes Bash, Write, and Edit tools to update files and execute project-related commands. \n
- Sanitization: The skill does not implement sanitization or filtering of the codebase content before it is processed by the AI agent.
Audit Metadata