brand-logo

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

• Third-party content exposure detected (low risk: 0.10). The skill retrieves brand logos and associated JSON from user-specified domain endpoints (img.replynodes.com and api.replynodes.com), where the agent must actively search or fetch specific URLs provided by the user.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill relies on third-party remote endpoints (img.replynodes.com and api.replynodes.com) with unknown or arbitrary third-party publisher provenance to retrieve logos and API data during runtime, representing an unverifiable runtime external dependency.