skills/ruvnet/ruflo/trader-regime/Gen Agent Trust Hub

trader-regime

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the neural-trader package from the NPM registry. The use of the --ignore-scripts flag is a positive security practice that prevents unauthorized code execution during the package installation phase.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands via npx to perform analysis. This introduces a potential command injection vector if user-supplied parameters (like symbols or tickers) are included in the command string without adequate sanitization.
  • [PROMPT_INJECTION]: The skill features an indirect prompt injection attack surface because it processes untrusted data from external tool outputs.
  • Ingestion points: Output generated by the neural-trader CLI tool in steps 2 and 3.
  • Boundary markers: None provided to distinguish data from instructions.
  • Capability inventory: Includes the Bash tool for shell execution and memory management tools for data persistence.
  • Sanitization: No explicit logic is defined to sanitize or validate the content received from the external command before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 03:01 PM
Security Audit — agent-trust-hub — trader-regime