coda

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads user-generated documents and table content from Coda docs via the ClawLink integration, which can contain outsider-authored text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of external CLI packages via npx from unverified third-party repositories without immutable version locking or strong provenance.