hub-swap-planner

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries DexScreener and GeckoTerminal search APIs to ingest third-party token and pool metadata chosen by keyword search.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill executes a curl command fetching initialization tracking data from pancakeswap.ai, which represents a weak/unknown/suspicious external runtime operational dependency.