crypto-liquidity-data

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is to retrieve and format public financial data. It lacks any script execution, file system access, or network operations targeting sensitive information.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved via WebSearch and WebFetch (e.g., CrossBorder Capital commentary or FRED data). While these are untrusted ingestion points, the skill has a restricted capability set (data retrieval and formatting) and does not utilize dangerous tools like shell execution or file writing, which effectively mitigates the impact of potential indirect injections.
  • [COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or system interactions present in the instructions or metadata.
  • [DATA_EXFILTRATION]: The skill does not access local sensitive paths (e.g., .ssh, .aws) or environment variables. All network activities are directed towards well-known public financial data providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 02:21 PM
Security Audit — agent-trust-hub — crypto-liquidity-data