marketing-content-pipeline-automation

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

• Third-party content exposure detected (low risk: 0.10). The required workflow crawls and ingests external web and social media content (TechCrunch, Twitter, LinkedIn) during topic research, which is then fed into LLM prompts.

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

• Potentially malicious external URL detected (high risk: 0.70). The repository cloned in the installation instructions is an arbitrary third-party personal repository (pennydinh), presenting an unverifiable operational dependency under the dependency gate.