Skills
skills/yorkeccak/scientific-skills/drug-labels-search/Gen Agent Trust Hub

drug-labels-search

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill utilizes local scripts for searching and setup.
  • [EXTERNAL_DOWNLOADS] (LOW): The skill connects to api.valyu.ai to fetch data.
  • [PROMPT_INJECTION] (LOW): Indirect prompt injection surface (Category 8) detected. Evidence: 1. Ingestion points: FDA drug label content from Valyu API. 2. Boundary markers: Absent. 3. Capability inventory: Local script execution (scripts/search). 4. Sanitization: None mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:36 PM