ai-listening

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads external X posts, GitHub content, and sitemaps via the new-term-radar command, which ingests outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning an arbitrary third-party personal GitHub repository (https://github.com/zhuyansen/new-term-radar) to execute its toolchain, presenting a weak/unknown/suspicious operational dependency resulting in a high tier.