parallel-develop

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The script intentionally auto-approves an interactive "trust" prompt and programmatically injects instructions into spawned AI worker panes, which enables external AI processes to access repository worktrees and potentially exfiltrate sensitive data without explicit human consent.

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required workflow takes outsider-authored GitHub issue text via gh issue view <number> (Step 1: “Validate Issues”) to confirm existence, which the runtime then exposes to the spawned Claude Code workers as part of solving those issues.