codex-utils

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for utilizing built-in agent capabilities for planning, web browsing, and utility tasks. It does not include any code, external dependencies, or instructions to override safety guidelines.
  • [PROMPT_INJECTION]: The skill instructions facilitate the ingestion of untrusted data from external websites via web tools, representing an indirect prompt injection surface. Ingestion points: External web content retrieved via web tools in SKILL.md. Boundary markers: Absent. Capability inventory: Local file inspection and tool discovery. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 09:02 AM
Security Audit — agent-trust-hub — codex-utils