The Agent Skills Directory

[SAFE]: The skill's primary purpose is to facilitate cryptocurrency trading where the user maintains control of their private keys.
[CREDENTIALS_UNSAFE]: While the skill references sensitive environment variables like AVE_EVM_PRIVATE_KEY and AVE_MNEMONIC, these are documented as local requirements for transaction signing. No hardcoded secrets or evidence of key exfiltration were found.
[EXTERNAL_DOWNLOADS]: The skill mentions pip install -r scripts/requirements.txt for setup. While the content of requirements.txt was not provided, the described dependencies (eth-account, solders) are standard libraries for blockchain interactions.
[DATA_EXFILTRATION]: Network operations are directed to bot-api.ave.ai, which is the official API endpoint for the service described in the skill's metadata. No suspicious third-party domains were found.
[PROMPT_INJECTION]: The instructions provide clear boundaries for the agent (e.g., 'DO NOT use this skill for...') and follow standard operational procedures without attempting to bypass safety filters.

ave-trade-chain-wallet