ai-content-pipeline

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

• Third-party content exposure detected (low risk: 0.10). The workflow references a web search tool (Tavily Search) in Pattern 3 (line 45) and an app registry/documentation links, but the skill itself describes a content pipeline configuration guide using CLI commands rather than ingesting outsider-authored content streams.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an installation script from raw.githubusercontent.com for the inference-sh/skills repository, which represents an unverified third-party runtime dependency.