open-targets

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to interact with the Open Targets Platform API and python3 -m json.tool for formatting results. These are standard and expected behaviors for a data retrieval skill.
  • [EXTERNAL_DOWNLOADS]: The skill connects to api.platform.opentargets.org. This is the official and well-known endpoint for the Open Targets Platform, a public resource for drug discovery and target validation.
  • [DATA_EXFILTRATION]: No sensitive local data access or exfiltration patterns were detected. All network operations are directed at the official API endpoint for the stated purpose of the skill.
  • [PROMPT_INJECTION]: The skill contains no instructions designed to bypass safety filters or override agent behavior. The included 'Data Integrity Rule' is a benign instruction aimed at preventing model hallucinations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 11:30 PM
Security Audit — agent-trust-hub — open-targets