loop-setup
Warn
Audited by Snyk on Jun 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill writes
.loop/config.mdwith concrete shell commands for the chosen backend (e.g.,gh issue view <n> --comments/glab issue view <n> --comments), and at runtime the agent will ingest outsider-authored issue bodies/comments from GitHub/GitLab via those commands.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata