skills/aipoch/medical-research-skills/single-drug-faers-safety-profile-research-planner/Gen Agent Trust Hub
single-drug-faers-safety-profile-research-planner
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or unauthorized operations were detected in the skill instructions or supplementary files. The workflow adheres to standard pharmacovigilance methodologies and emphasizes scientific accuracy and transparency through mandatory disclaimers and risk reviews.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied research parameters and retrieves external literature (Step 4.5), representing an indirect prompt injection surface.\n
- Ingestion points: User input in Step 1 of SKILL.md and external literature search results referenced in literature-retrieval-and-citation.md.\n
- Boundary markers: The skill requires structured output sections and mandatory disclaimers, although it does not use specific delimiters like XML tags for external data.\n
- Capability inventory: The skill workflow involves searching and planning based on external pharmacovigilance research literature.\n
- Sanitization: The instructions implement robust mitigations, including mandatory resolvable DOI verification and explicit prohibitions against fabricated references, which serve to validate the authenticity of external content and prevent the ingestion of malicious instructions.
Audit Metadata