productboard

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

• Third-party content exposure detected (medium risk: 0.30). Productboard collects user feedback and product notes which can contain outsider-authored free text ingested by the agent during read operations.

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 npx @useclawlink/cli, which downloads and runs external code from npm without a verifiable repository locator or explicit provenance, representing a weak/unknown runtime operational dependency.