orchestration

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

• Third-party content exposure detected (low risk: 0.10). The workflow involves fetching external documentation and audit guidelines via specified URLs like ethskills.com and scaffoldeth.io, which presents a low-risk exposure to external content.

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

• Potentially malicious external URL detected (high risk: 0.70). The document references remote Markdown files on ethskills.com and bgipfs.com which are fetched during agent workflows as instructions and skill material, representing unverified third-party operational dependencies.