blueprint-retention

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No security issues detected. The skill contains only instructional text and references a local template file. It does not utilize any tools, perform network operations, or access sensitive system resources.
  • [INDIRECT_PROMPT_INJECTION]: Ingestion point: The skill references a local file 'templates/psychology/retention-design-sheet.md' as a template. Boundary markers: No delimiters or ignore instructions are present for the template content. Capability inventory: No subprocess calls, code execution, file-writes, or network operations are available in this skill. Sanitization: No sanitization or validation of the template content is performed. While the skill represents a data ingestion surface, the lack of capabilities prevents exploitation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 11:36 AM
Security Audit — agent-trust-hub — blueprint-retention