create-feature

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard build tools (dotnet build, nx build) and a local project utility script (python .claude/scripts/code_graph). These commands are essential for the skill's stated purpose of feature scaffolding and verification within a development environment.- [PROMPT_INJECTION]: The skill uses authoritative instructional markers (e.g., "MANDATORY", "IMPORTANT", "MUST ATTENTION") to enforce a specific, task-oriented workflow. These are used to ensure the agent performs safety-critical steps like reading existing code and seeking user approval, rather than to bypass safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:18 AM
Security Audit — agent-trust-hub — create-feature