prd-grade-fe

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow consumes arbitrary web page content via URL intake (Route C study <URL>), which is fetched and processed at runtime.

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

• Potentially malicious external URL detected (high risk: 0.70). The script fe-gate.sh executes npx -y impeccable@3.6.1, which fetches and executes a package at runtime from the npm registry without pinned digests, constituting a weak/unknown/suspicious operational dependency.