metacpan

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

• Third-party content exposure detected (low risk: 0.10). The skill searches MetaCPAN, a public package registry containing community-authored module documentation and descriptions, which constitutes low-risk outsider-authored free text ingestion.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill connects to a remote third-party MCP server hosted at unbrowse.ai, which supplies operational tools and behavior-defining instructions, representing an unverified third-party runtime dependency with medium provenance tier.