opsx-verify

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute local command-line tools, specifically openspec for status checks and codegraph for code exploration and synchronization.
  • [INDIRECT_PROMPT_INJECTION]: The instructions pass user-supplied arguments directly into shell commands, which presents a surface for potential command injection if the agent does not properly escape the input.
  • Ingestion points: Change names and key terms provided via the /opsx:verify slash command.
  • Boundary markers: None identified; user input is placed directly within command strings.
  • Capability inventory: The skill uses subprocess-equivalent shell commands for file system interactions and tool execution.
  • Sanitization: No explicit sanitization or validation of the user-provided <name> or <key terms> is performed before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 05:53 PM
Security Audit — agent-trust-hub — opsx-verify