curriculum-research

Warn

Audited by Snyk on Feb 15, 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's workflow explicitly instructs the agent to "Use WebSearch to gather" core concepts and "Use WebSearch to identify" relevant standards (see SKILL.md steps 2 and 3), so the agent is expected to fetch and read open/public web content (potentially untrusted/user-generated) as part of its operation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:38 PM