git-worktree-agent-workflow

Warn

Audited by Snyk on Feb 23, 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.md subagent template explicitly shows the orchestrator passing "Issue #{N}: {issue title} {issue description}" into agents, meaning agents will ingest and act on user-generated issue text (untrusted third‑party content) as part of their workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 01:34 PM