workflow-initializer

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches optional plugin SKILL.md files and manifests from GitHub via URLs without prior selection of specific external items, but the referenced domain is a trusted GitHub raw repository controlled by the skill repository.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch plugin skills and workflow manifests from an arbitrary personal GitHub repository (albertmartorell1975), constituting an unverifiable external runtime dependency with weak provenance.