opentargets-skill

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Network Operations: The skill communicates exclusively with the official Open Targets Platform API at https://api.platform.opentargets.org/api/v4/graphql. This is the intended purpose of the skill and follows standard integration patterns.
  • File System Interaction: The scripts include functionality to save raw GraphQL responses to the local file system. This is gated by a save_raw parameter and defaults to /tmp directories, which is a standard practice for temporary data storage.
  • Command Execution: The skill uses Python scripts to process data. These scripts read input from stdin and perform standard data transformation and network requests. No arbitrary shell command execution or privilege escalation patterns were detected.
  • Data Handling: The skill includes logic to compact and truncate large GraphQL responses, which helps manage context window limits and prevents large, unparsed data blobs from being injected into the conversation unnecessarily.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 03:58 AM
Security Audit — agent-trust-hub — opentargets-skill