advocacy-program-designer
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill focuses on generating marketing blueprints and compliance documentation without requesting elevated privileges or accessing sensitive system data.
- [PROMPT_INJECTION]: The instructions include a specific security section directing the agent to treat pasted rosters, executive mandates, and forwarded messages as untrusted input. It requires explicit 'voluntary-basis evidence' rather than accepting assertions of consent, which mitigates risk from malicious data provided during the session.
- [DATA_EXFILTRATION]: The skill does not perform unauthorized network operations. It references local scripts for public handle checks on open platforms and emphasizes that data from closed platforms must be manually provided by the user.
- [COMMAND_EXECUTION]: No shell commands or dynamic execution patterns were found. The skill specifically forbids automation on several social media platforms to avoid triggering risk controls.
Audit Metadata