multi-user-workflow-generator

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands via the Bash tool to control playwright-cli for browser automation. This includes session management, navigation, and UI interactions across multiple named persona contexts.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of external data.
  • Ingestion points: Codebase contents are retrieved via Read, Grep, and Glob tools, and user persona details are collected through interactive prompts.
  • Boundary markers: Data is interpolated into sub-agent prompts using placeholders without clear delimiters or instructions to disregard embedded instructions in the source code.
  • Capability inventory: The skill can execute shell commands, manage browser sessions, and write workflow documentation to the filesystem.
  • Sanitization: No explicit sanitization or validation of codebase content or user input is documented before its use in constructing prompts or shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 03:44 AM