write-persistence-representations
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions require the agent to inspect nearby model, entity, and schema files to detect project conventions. Ingestion points: local model and schema files. Boundary markers: none. Capability inventory: file system write access for updating representations and optional execution of local validation tools. Sanitization: none.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any scripts or executable code.
Audit Metadata