identity-work
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and JSON test data. No shell scripts, Python files, or Node.js modules are included.
- [SAFE]: No network operations, file system access, or credential requirements were detected in any of the analyzed files.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input regarding personal life scenarios.
- Ingestion points: User prompts involving identity, self-deception, or change are ingested via the agent's primary interface.
- Boundary markers: None explicitly defined in the prompt interpolation logic.
- Capability inventory: None. The skill does not use any tools, file-writing, or network capabilities.
- Sanitization: Not present, but unnecessary as the skill has no actionable capabilities for an attacker to exploit.
Audit Metadata