healthcare-business-analyst
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted external data.
- Ingestion points: As defined in Section 12, the skill processes version-controlled Markdown, structured records, diagrams, API specifications, and schemas.
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill is granted significant authority to approve healthcare workflows, acceptance criteria, and technical designs, and to produce Business Decision Records (BDRs).
- Sanitization: There are no explicit instructions for the agent to sanitize or escape content from external documents before including it in its own analysis or prompts.
Audit Metadata