design

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill contains no executable code, scripts, or binaries. It consists entirely of natural language instructions.
  • [SAFE]: No network operations, external downloads, or remote resource fetches are performed.
  • [SAFE]: No sensitive system file access, credential harvesting, or data exfiltration patterns were identified.
  • [PROMPT_INJECTION]: The skill instructs the agent to read and follow a local file (.agents/workflows/design.md). While processing external content can present an indirect prompt injection surface, reading local project-specific workflow documentation is the primary intended purpose of this skill and is considered a safe operational pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 07:04 AM