identity-mirror
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and psychological frameworks. It does not define any executable code or use system-level tools.
- [DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths were detected. The skill does not perform any network operations to external domains.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (psychographic profiles) but lacks the capability to execute commands that could lead to harm.
- Ingestion points: Processes external psychographic data and customer profiles (SKILL.md).
- Boundary markers: Absent; the skill does not use specific delimiters to isolate untrusted input.
- Capability inventory: None. The skill does not use subprocesses, file operations, or network tools.
- Sanitization: Absent; no input validation is performed on the ingested psychographic data.
- [REMOTE_CODE_EXECUTION]: No remote packages or scripts are downloaded or executed. The skill references other agent skills via skill-chaining (@ notation), which is a standard platform feature for task delegation.
Audit Metadata