workflows-review

Fail

Audited by Snyk on Feb 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The prompt instructs agents to suppress/discard findings for specific protected artifact paths and mandates automatic todo creation without user approval, which deceptively narrows/changes the "exhaustive" review behavior and hides potential issues outside the stated purpose.

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests user-generated PR content from GitHub (e.g., "gh pr view --json", GitHub URLs / PR number inputs and "PR content" used by multiple review agents), which is untrusted third‑party content the agent is expected to read and interpret as part of its workflow.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 04:11 PM