skillpack-check

Warn

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill documentation explicitly instructs the agent to process an 'actions' array from a JSON report and run each string through 'eval'. This pattern allows for arbitrary shell command execution based on dynamic content provided by the 'gbrain' binary at runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect injection if the 'gbrain' tool's output is compromised or contains unexpected data. Ingestion points: JSON report from 'gbrain skillpack-check'. Boundary markers: Absent. Capability inventory: Shell command execution via 'eval' in the shell tool. Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill's primary function is to manage system state through shell commands, specifically leveraging the 'gbrain' CLI for diagnostics and remediation tasks.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 29, 2026, 06:18 PM
Security Audit — agent-trust-hub — skillpack-check