skills/iliaal/whetstone/ia-md-docs/Gen Agent Trust Hub

ia-md-docs

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted project data (e.g., README.md, package.json) to generate or update documentation. This creates a surface where malicious instructions embedded in a project's files could influence the agent's behavior during the update process.
  • Ingestion points: Reads package.json, pyproject.toml, composer.json, README.md, and other project files via cat and ls (referenced in SKILL.md and references/init-agents.md).
  • Boundary markers: None explicitly defined to separate untrusted project content from agent instructions, though the skill focuses on extracting specific metadata.
  • Capability inventory: Uses mv, ln, cp, and file write operations to modify documentation files (referenced in SKILL.md and references/init-agents.md).
  • Sanitization: No specific sanitization or filtering of external content is described before interpolation into the documentation templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 06:03 PM
Security Audit — agent-trust-hub — ia-md-docs