life-open-project

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied strings for project outcomes and success criteria, incorporating them into project notes and registry files. This creates a surface for indirect prompt injection where malicious instructions could be embedded in data processed by the agent.
  • Ingestion points: User-provided text for 'outcome' and 'done_when' fields defined in SKILL.md.
  • Boundary markers: No delimiters or ignore-instruction warnings are specified for the interpolation of user content.
  • Capability inventory: The skill performs file system writes to create project notes in 'layout.projects_active' and updates registry files.
  • Sanitization: The skill does not define validation, escaping, or filtering for the interpolated external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 05:22 AM
Security Audit — agent-trust-hub — life-open-project