facility-outreach-personalizer
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily composed of markdown instructions, templates, and pseudo-code for text generation. No functional code or scripts that interact with the host system were detected.
- [PROMPT_INJECTION]: No patterns of instruction override, safety bypass, or role-play injection were identified. The skill explicitly includes logic to reject 'scary' or 'fear-based' tones, reinforcing safety boundaries.
- [DATA_EXFILTRATION]: The skill uses publicly available California Community Care Licensing Division (CCLD) data as input. There is no evidence of the skill accessing sensitive local files, credentials, or environment variables.
- [REMOTE_CODE_EXECUTION]: No remote script downloads, package installations, or dynamic code execution patterns (like eval or exec) are present.
- [COMMAND_EXECUTION]: The skill does not utilize shell commands or perform any subprocess operations. It operates entirely as a content generation assistant.
Audit Metadata