tutor

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md "Additional Guidelines" explicitly instruct the agent to "use web search (and in the case of coding related topic code in open source repositories) to fortify your understanding," which requires fetching and interpreting public third-party content (web pages/open-source repos) that could influence the agent's decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 03:58 AM