managing-conditions-of-participation
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves the ingestion and analysis of external, potentially untrusted healthcare documentation, which presents a surface for indirect prompt injection attacks.
- Ingestion points: The skill requires processing external data as defined in "Checkpoint A — Intake Questions" and the "Required Documents" list, including CMS-2567 forms, accreditation reports, and medical staff files.
- Boundary markers: The instructions lack specific boundary markers or delimiters to isolate the content of external documents from the agent's core instructions.
- Capability inventory: The skill focuses on assessment and monitoring; it does not define active capabilities such as file writing, network operations, or shell command execution.
- Sanitization: There are no provided mechanisms for sanitizing, filtering, or validating the content of external regulatory documents before they are processed by the agent.
Audit Metadata