project-docs-maintainer

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted markdown content from a user-provided workspace, which creates a surface for indirect prompt injection.
  • Ingestion points: The scripts 'scripts/skills_readme_maintenance.py' and 'scripts/roadmap_alignment_maintainer.py' read content from README.md and ROADMAP.md files.
  • Boundary markers: The skill does not implement delimiters or 'ignore instructions' markers when passing the contents of these files into the agent's context.
  • Capability inventory: The skill has the capability to write to and modify files within the workspace, specifically markdown documentation.
  • Sanitization: The scripts use regular expressions for text manipulation but do not sanitize or filter the content for potential malicious instructions targeted at the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 04:27 AM