event-code-of-conduct
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements an interview-based workflow that collects untrusted user data to generate event policies and runbooks.
- Ingestion points: User responses to the eight-question interview in
SKILL.mdare integrated into the agent's context to customize the generated deliverables. - Boundary markers: The instructions lack explicit delimiters to isolate user-provided interview answers from the system instructions.
- Capability inventory: The skill is limited to document generation and lacks high-risk capabilities such as arbitrary command execution, file system modification, or network operations.
- Sanitization: No input validation or sanitization is performed on the user's interview responses before they are processed by the model.
Audit Metadata