documentation-guide

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of documentation guidelines and contains no executable code, network operations, or external downloads. All metadata and instructions are consistent with the stated purpose of documentation enforcement.
  • [PROMPT_INJECTION]: The skill operates on local project files (Markdown, Python source code) to verify documentation compliance, which presents a surface for indirect prompt injection (Category 8).
  • Ingestion points: Reads README.md, CHANGELOG.md, ADR files, and Python source code for docstring verification.
  • Boundary markers: No explicit delimiters or instruction-ignore warnings are specified for the ingested content.
  • Capability inventory: Uses Read, Write, Edit, Grep, and Glob tools for file management and analysis.
  • Sanitization: No content filtering or escaping is performed on the files being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 06:45 PM