drug-combination-synergy
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input which represents a standard surface for indirect prompt injection.
- Ingestion points: User-supplied parameters including
drug_A,drug_B,indication, andtumor_typesinSKILL.mdare ingested into the agent context. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the user-provided drug names or clinical descriptions.
- Capability inventory: The skill integrates with multiple MCP search tools (
mcp_virtual-mcp-pharma-intelligence__*,mcp_patent-search__patsnap_search) and theofficetoolchain for file creation. - Sanitization: There is no evidence of explicit validation or sanitization of the pharmaceutical names or SMILES strings before they are used in tool invocations.
Audit Metadata