codex-cli-specialist

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly documents remote skill discovery and distribution (e.g., "Registry: Remote skills index (when configured)" under "Skill Discovery and Locations" and GitHub-based install examples like git clone https://github.com/org/skills-repo.git), meaning the agent can fetch and load untrusted third‑party SKILL.md / agents/openai.yaml content that directly defines instructions and tools used at runtime.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 03:55 AM