persona-it-admin
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to process external data that could contain malicious instructions aimed at influencing agent behavior.
- Ingestion points: The persona is instructed to review "pending IT requests" through workflows and monitor "audit logs" using administrative tools in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore" rules to help the agent distinguish between data and instructions within the logs or requests.
- Capability inventory: The skill allows the agent to perform high-privilege actions such as creating, suspending, or updating user accounts and modifying organizational security policies.
- Sanitization: There are no defined mechanisms for sanitizing or validating the content of external requests or log entries before they are processed by the agent.
Audit Metadata