open-wrap-url

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill executes a local Node.js script (scripts/open-wrap-url.js) using the Bash tool to automate the browser opening process. This is the intended functional path for the skill to handle environment-specific URL redirection.
  • Indirect Prompt Injection Surface: The skill processes external inputs by interpolating user-provided IDs into a shell command.
  • Ingestion points: User-supplied --app-id and --env-id values are read from $ARGUMENTS in SKILL.md.
  • Boundary markers: No specific boundary delimiters or safety instructions are explicitly defined to isolate user-provided data within the prompt instructions.
  • Capability inventory: The skill is configured with the Bash tool and interacts with system-level command execution to trigger the browser.
  • Sanitization: The command template uses double quotes to wrap argument values, providing a standard layer of protection for shell argument passing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 07:03 AM
Security Audit — agent-trust-hub — open-wrap-url