doctor
Warn
Audited by Snyk on Mar 2, 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). The skill's Auto-Fix step "Fix: Missing/Outdated AGENTS.md" explicitly fetches raw markdown from the public URL https://raw.githubusercontent.com/Yeachan-Heo/oh-my-codex/main/docs/AGENTS.md and writes it into the local AGENTS.md, so the agent ingests untrusted public GitHub content that could contain instructions influencing agent configuration and behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's auto-fix step performs a runtime WebFetch from https://raw.githubusercontent.com/Yeachan-Heo/oh-my-codex/main/docs/AGENTS.md to fetch and write AGENTS.md, which can inject remote agent configuration/instructions that directly control agent behavior.
Audit Metadata