Skills
Navigate
skills/taehwandev/moru-core/product-architecture-delivery/Gen Agent Trust Hub

product-architecture-delivery

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's workflow interpolates raw user input (<USER_REQUEST>) into shell commands executed via <MORU_LAUNCHER>.
  • Ingestion points: The <USER_REQUEST> variable in references/current-guidance.md is populated from untrusted user input.
  • Boundary markers: No specific boundary markers or instructions to treat the input as untrusted data are present in the documentation.
  • Capability inventory: The skill utilize shell command execution for launching workflows and running diagnostic scripts including workflow.py, agent-preflight.py, and agent-finish-check.py as detailed in references/current-guidance.md.
  • Sanitization: No sanitization or escaping logic is described for the interpolated user input before it is passed to the shell environment.
  • [COMMAND_EXECUTION]: The workflow guidance explicitly instructs the agent to execute various local utility and diagnostic scripts.
  • Evidence: references/current-guidance.md references the execution of workflow.py route, agent-preflight.py, and agent-finish-check.py as lower-level diagnostic fallbacks when standard hooks are unavailable.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 05:22 AM