plan-first-development

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs "Have Claude Code search the web and update them to latest versions" in references/decision-tracking.md, which requires fetching and integrating public web content (untrusted/user-generated) that the agents will read and use to update plans and docs, enabling indirect prompt injection risk.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 04:28 AM