crypto-bd-agent

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

• Third-party content exposure detected (medium risk: 0.30). The skill describes an AI agent that scans public cryptocurrency data and community/forum signals, which allows outsiders to submit arbitrary free text into monitored token channels and project sources.

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

• Potentially malicious external URL detected (medium risk: 0.30). The referenced GitHub repository is an unofficial personal/project repository that acts as an external dependency link without formal enterprise attestation or immutable verification, presenting an unverifiable runtime external dependency.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (medium risk: 0.30). The skill describes an AI agent for crypto business development that mentions x402 micropayments for paid intelligence sources (SKILL.md:23,98). These micropayments represent a direct financial operation (payments for API calls). However, the skill explicitly requires "explicitly approved endpoints with an authorized per-call/total budget and validated payment terms" (SKILL.md:216) and "enforceable budget limits" on a dedicated wallet (SKILL.md:240), establishing qualifying independent/enforced budget limits and controls for the direct payment operations. Therefore, the severity is medium.