dd-oci-integration

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow fetches and executes a skill script via curl from a GitHub repository (codeload.github.com), which ingests external repository content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill downloads and executes arbitrary code/skills from a GitHub repository via curl and tar without integrity verification, creating an unverifiable runtime external dependency from a common/reputable unofficial source.