flow-next-prime

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes local codebase content, which is a surface for indirect prompt injection. However, this is mitigated by strict guardrails that prevent code modification and require interactive user consent via the AskUserQuestion tool.
  • [COMMAND_EXECUTION]: Executes read-only verification commands such as listing tests or checking build help menus to confirm environment health.
  • [EXTERNAL_DOWNLOADS]: Includes templates that reference well-known development tools from trusted sources, specifically the pre-commit and Ruff projects.
  • [CREDENTIALS_UNSAFE]: Promotes security best practices by auditing .gitignore files and encouraging the use of .env.example templates to prevent accidental secret exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 06:09 AM