doc-health-audit

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill orchestrates a pipeline that ingests untrusted data from documentation files, creating a surface for potential instruction injection via content analysis.
  • Ingestion points: Processes content from documentation directories (e.g., docs/, site/) and files like README.md through tools such as Read, Grep, and Glob.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the data being audited.
  • Capability inventory: Utilizes Bash for scope determination (e.g., git diff) and the Agent tool to coordinate specialized analysis skills that access and evaluate file content.
  • Sanitization: No evidence of sanitization, validation, or filtering of documentation content is described before the data is processed by the orchestrated analysis phases.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 12:41 PM
Security Audit — agent-trust-hub — doc-health-audit