Skills
Navigate
skills/proffesor-for-testing/agentic-qe/V3 CLI Modernization/Gen Agent Trust Hub

V3 CLI Modernization

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill implements a ModularCommandRegistry and a WorkflowOrchestrator in SKILL.md designed to register and execute CLI commands, including complex multi-step workflows.
  • [INDIRECT_PROMPT_INJECTION]: The WorkflowOrchestrator in SKILL.md includes functionality to generate and execute workflows based on a natural language 'intent' string, which presents a surface for indirect prompt injection.
  • Ingestion points: User-supplied intent strings processed by generateWorkflowFromIntent in SKILL.md.
  • Boundary markers: None identified in SKILL.md to delimit user input from instruction templates.
  • Capability inventory: Command execution via ModularCommandRegistry.executeCommand as implemented in SKILL.md.
  • Sanitization: The code snippets in SKILL.md do not demonstrate sanitization or validation of the generated workflow steps before they are executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 12:25 PM