curl
Warn
Audited by Snyk on Mar 7, 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). SKILL.md explicitly instructs the agent to fetch and inspect arbitrary target domains/URLs using curl and wrapper scripts (e.g., "curl -vI https://" and scripts/curl/debug-http-response.sh), meaning it ingests untrusted public web content that the agent must read/interpret and that can influence subsequent actions.
Audit Metadata