tooluniverse-adverse-outcome-pathway
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied compound names to query external scientific databases (AOPWiki, PubChem, and CTD), creating a surface where untrusted data enters the agent context.
- Ingestion points: Chemical names and parameters provided by the user in tools such as
PubChem_get_CID_by_compound_name,AOPWiki_list_aops, andCTD_get_chemical_gene_interactionsas described in SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers to isolate user-supplied chemical names from the operational logic.
- Capability inventory: The skill possesses capabilities to perform network-based data retrieval via scientific API tools across all phases of the workflow.
- Sanitization: There are no instructions for validating, escaping, or filtering the input terms before they are interpolated into tool calls.
Audit Metadata