cli-coingecko

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the cg CLI tool to fetch market data. It uses non-interactive commands and inspects the command catalog (cg commands -o json) to ensure only supported operations are performed.
  • [INDIRECT_PROMPT_INJECTION]: The skill manages potential injection through user-supplied coin names and symbols by routing them through a validation script. The scripts/build-url.py utility uses a strict regex (^[a-z0-9]+(?:-[a-z0-9]+)*$) for coin IDs and standard date parsing, preventing malicious strings from influencing the generated URLs or command arguments.
  • [REMOTE_CODE_EXECUTION]: A mechanism for updating the CLI tool (cg update) is documented but requires explicit user approval and provides a dry-run option, mitigating the risk of unauthorized software changes.
  • [DATA_EXFILTRATION]: The instructions contain a clear directive to never expose API keys or private wallet data to external endpoints, maintaining a focus on public market data.
  • [DYNAMIC_EXECUTION]: The skill utilizes a Python helper script via the uv runner. This script is used solely for URL construction and contains robust input validation to ensure safety during execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM
Security Audit — agent-trust-hub — cli-coingecko