value-prop-builder

Warn

Audited by Snyk on Mar 5, 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.md "Research Support" section explicitly instructs the agent to "Use WebSearch to find relevant messaging examples" (competitor positioning, headlines), so the skill can fetch and interpret open/public web content that could contain untrusted, user-generated instructions affecting its messaging and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 04:06 AM