theangry-people-note-bootstrap

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external information about people or agents to generate documentation.
  • Ingestion points: External context provided by the user or read from repository templates (SKILL.md).
  • Boundary markers: None explicitly defined to separate untrusted content from agent instructions.
  • Capability inventory: File system write access to defined paths like PEOPLE/<slug>.md.
  • Sanitization: The skill includes extensive 'Privacy Rules' to exclude sensitive data but does not include instructions for sanitizing content to prevent the execution of embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 05:52 PM
Security Audit — agent-trust-hub — theangry-people-note-bootstrap