claudeception

Warn

Audited by Snyk on Feb 21, 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 "Step 3: Research Best Practices (When Appropriate)" explicitly instructs the agent to search the web, review top results, and incorporate/cite external URLs into created skills, which requires ingesting untrusted public web content that can influence solutions and subsequent tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 08:20 AM