doc-create

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The agent is instructed to run ls docs/ to list existing documentation categories. This is a standard read-only command used to ensure new files are correctly categorized.
  • [PROMPT_INJECTION]: The skill uses previous conversation history to generate documentation, presenting an indirect injection surface. 1. Ingestion points: previous conversation messages in SKILL.md; 2. Boundary markers: none; 3. Capability inventory: directory listing and file creation; 4. Sanitization: none. The risk is low because the skill produces static Markdown content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 01:47 PM
Security Audit — agent-trust-hub — doc-create