skills/getlark/skills/create-workflow/Gen Agent Trust Hub

create-workflow

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the @getlark/cli Node.js package. This is the official command-line tool provided by the vendor (Getlark) for interacting with their platform.
  • [COMMAND_EXECUTION]: The skill executes shell commands via the Bash tool to interface with the getlark CLI. This is the primary function of the skill and is scoped to the vendor's official toolset.
  • [PROMPT_INJECTION]: The skill processes user-provided test descriptions and interpolates them into shell commands, which represents an indirect prompt injection surface.
  • Ingestion points: Natural language descriptions provided by the user via the description argument or interactive prompt.
  • Boundary markers: The skill instructions specifically direct the agent to wrap the derived name and full description in double quotes when constructing the CLI command.
  • Capability inventory: The skill uses the Bash tool to execute the vendor CLI, which performs network operations to the Getlark API.
  • Sanitization: No explicit sanitization or escaping logic is provided beyond standard shell quoting of arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 07:14 PM
Security Audit — agent-trust-hub — create-workflow