competitor-ads-analyst

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

• Third-party content exposure detected (low risk: 0.10). The required workflow directs the agent to search and extract ad copy from public ad libraries (Meta, Google, TikTok, LinkedIn) where competitors can publish arbitrary text.

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

• Potentially malicious external URL detected (high risk: 0.70). The installation command clones a GitHub repository to install skill files locally, constituting an inbound operational dependency from a personal repository with weak/unknown provenance.