github-navigator
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and clones public GitHub repositories (e.g., SKILL.md's "Deep Analysis Mode" clone to /tmp and numerous gh api examples like gh api repos/OWNER/REPO/contents/PATH), causing the agent to read and interpret untrusted, user-generated content from github.com as part of its workflow.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill clearly performs runtime fetches of arbitrary repository content (e.g., via git clone https://github.com/OWNER/REPO.git and gh api repos/OWNER/REPO/contents/PATH) which are pulled into the agent’s context for analysis and thus can directly influence prompts/behavior and introduce remote code/content the skill depends on.
Audit Metadata