doc-health-audit

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git commands, such as git diff --name-only, to identify which documentation files have changed. This is a standard method for scoping audits in development workflows.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes content from documentation files that may be untrusted. This is a known risk for any tool that analyzes external text, but the skill's logic is focused on generating reports and coordinating audit phases.
  • Ingestion points: Documentation files in directories like docs/ and site/, as well as README.md and git-identified changes.
  • Boundary markers: None specified in the current instructions.
  • Capability inventory: Uses Bash for git, Read, Grep, Glob for file access, and the Agent tool to delegate tasks to other audit skills.
  • Sanitization: The skill analyzes and summarizes findings but does not mention explicit sanitization of the input documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:13 PM