swap-planner

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses WebSearch and fetches token data from third-party APIs (DexScreener and DefiLlama) where outsider-authored token metadata and search results can introduce untrusted free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to execute cURL commands against third-party public APIs (DexScreener and DefiLlama) to retrieve live price and token data at runtime, constituting a common/reputable unofficial operational dependency.