ranger
Warn
Audited by Snyk on Jul 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: 0.75). Outsider free text can enter the LLM context via GitHub issues: the skill runs
gh issue listand passes issue titles/bodies/comments (untrusted user-authored text) to explorer subagents as “raw pointers,” which the LLM then reads and uses for triage.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata