Skills
skills/duyet/codex-claude-plugins/agent-loop-triage/Snyk

agent-loop-triage

Warn

Audited by Snyk on Jun 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.95). The skill uses gh issue view / gh pr view to fetch outsider-authored body and comments (and PR diff via --patch) from GitHub issues/PRs, which are free-form text written by other users and then ingested into the agent’s LLM context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 16, 2026, 03:12 AM
Issues
1
Security Audit — snyk — agent-loop-triage