genmedia

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

• Third-party content exposure detected (low risk: 0.10). The skill searches fal.ai documentation (genmedia docs) and catalogs (genmedia models), which ingest community-influenced search results and docs.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation of the genmedia CLI via https://genmedia.sh/install and https://genmedia.sh/install.ps1, which are third-party unofficial scripts that execute arbitrary code with weak provenance, meeting the criteria for a high-risk operational dependency.