game-ui-product-design

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a project initialization script scripts/init_project.py using a user-supplied <project-id> as a command-line argument. This execution pattern involves passing unverified input to a shell command.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external files to generate core project documentation, creating a vulnerability surface.\n
  • Ingestion points: The skill reads from user-provided files spec.md, research.md, and plan.md.\n
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in these input files.\n
  • Capability inventory: The skill is capable of writing files to the specs/ directory and executing a local Python script.\n
  • Sanitization: No sanitization or validation of the input file content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 03:10 PM
Security Audit — agent-trust-hub — game-ui-product-design