pyats-security

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries public CVE databases via NVD API, which returns outsider-authored/community-managed vulnerability descriptions and advisory free text into the agent context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill executes npx -y nvd-cve-mcp-server to fetch and run a package from the public npm registry without a verifiable publisher or integrity digest.