heroku

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

• Third-party content exposure detected (low risk: 0.10). The Heroku skill interacts with Heroku APIs and application data via the Membrane CLI, which may return user-generated application content or metadata depending on the specific apps managed.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the installation and execution of an npm package (@membranehq/cli) from an unverified public registry without checksum verification or established provenance, constituting an unverifiable runtime external dependency.