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
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:38 PM
Security Audit — agent-trust-hub — gsd-docs-update