planning-with-files

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to perform web/browser/search operations and to capture and act on browser results (see SKILL.md "The 2-Action Rule" / "Read Before Decide" and templates/findings.md "Visual/Browser Findings", plus examples.md showing "WebSearch"), which means it ingests untrusted public web content that can influence decision-making.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 01:14 AM