sexual-health-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted user-provided data in the form of sexual health records, screening history, and activity logs.
- Ingestion points: User input containing health records and historical data are processed to generate reports and risk assessments as described in the examples and scenarios in SKILL.md and references/detailed-guide.md.
- Boundary markers: The instructions do not define explicit boundary markers or delimiters (such as XML tags or triple quotes) to isolate user-provided data from the agent's instructions.
- Capability inventory: No custom scripts, shell commands, or specific tool-use capabilities are defined within the provided skill files.
- Sanitization: No explicit sanitization, input validation, or filtering logic is provided to handle potentially malicious instructions embedded within the user records.
Audit Metadata