systematic-review-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates medical research screening by processing external study data which may contain malicious instructions. 1. Ingestion points: Title and abstract screening, full-text review (SKILL.md). 2. Boundary markers: None; there are no instructions to the agent to disregard instructions embedded in the ingested text. 3. Capability inventory: The skill is restricted to prompt-based analysis and lacks script execution or network capabilities. 4. Sanitization: No sanitization of user-provided study data is described.
- [NO_CODE]: The skill consists entirely of instructional text and does not contain any executable scripts or configuration files.
Audit Metadata