hex-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements standard integration workflows for the Hex data platform, including project run management and scheduling.
  • [DATA_EXFILTRATION]: API authentication is handled securely via environment variables (HEX_API_TOKEN). Network communication is limited to the official Hex service domain (app.hex.tech).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Hex API responses. 1. Ingestion points: Hex API endpoints (/project/${projectId}/runs, /workspace/users, /workspace/groups, /workspace/connections) referenced in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Read, Write, Edit, Bash, Grep. 4. Sanitization: Handled via structured JSON parsing. While this represents an external data ingestion surface, the skill lacks high-risk capability chains that would lead to exploitable injection vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:44 AM
Security Audit — agent-trust-hub — hex-core-workflow-b