binance-web3-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external Binance Web3 API endpoints, creating a surface where malicious third-party content could influence the agent.
- Ingestion points: Processes token metadata, search results, social hype rankings, and security audit reports from
web3.binance.com. - Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the data returned from the API.
- Capability inventory: The skill performs network operations and shell command execution via the
uxcutility. - Sanitization: There is no evidence of sanitization or validation of the strings (such as token descriptions or social signals) fetched from the external API before they are incorporated into the agent's context.
Audit Metadata