harvest-rewards

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and parses live data from public third-party APIs and sites (e.g., infinity.pancakeswap.com, api.coingecko.com, api.dexscreener.com, configs.pancakeswap.com and dexscreener URLs) via the required Step 0/Step 1 calls and the references/*.py scripts, and those responses are read and used to compute pending rewards, USD values, and harvest recommendations that materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The included local Python scripts (references/fetch-*.py) run subprocess calls to pip to install the "requests" package at runtime—which will fetch and execute code from PyPI (e.g. https://pypi.org/project/requests) as a required dependency—so remote code is downloaded and executed during skill runtime.