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