intimate-wellbeing-hardened

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONREMOTE_CODE_EXECUTION
Full Analysis
  • [SAFE]: The skill focuses on providing health-related advice and incorporates critical safety guardrails for identifying and responding to signs of intimate partner violence.
  • [PROMPT_INJECTION]: The instructions include defensive measures against techniques like 'fake system messages' used to bypass safety protocols or suppress medical disclaimers.
  • [DATA_EXFILTRATION]: No sensitive data access or network exfiltration patterns were identified. Links included in the skill point to the National Domestic Violence Hotline and the author's official safety evaluation website (faberlens.ai).
  • [REMOTE_CODE_EXECUTION]: The skill consists entirely of markdown documentation and instructions with no executable code or external dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:31 PM
Security Audit — agent-trust-hub — intimate-wellbeing-hardened