query-token-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to the official Binance Web3 API (https://web3.binance.com) to retrieve token security audit data. This is consistent with the skill's stated purpose and uses a vendor-controlled domain.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data from user inputs and API responses, which can influence the agent's guidance.\n
- Ingestion points: The skill ingests user-supplied contractAddress and binanceChainId parameters from SKILL.md and processes the riskItems metadata returned by the Binance API.\n
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be hidden in token metadata or response fields.\n
- Capability inventory: The skill uses network POST requests and provides actionable security guidance that could be manipulated to suggest a malicious token is safe.\n
- Sanitization: The instructions do not specify any validation or sanitization of the data retrieved from the blockchain or the API before processing.
Audit Metadata