spec-driven

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional content that guides the agent through a software development lifecycle. It does not contain malicious code or exploit patterns.
  • [EXTERNAL_DOWNLOADS]: The README provides an installation command via git clone from the author's GitHub repository (github.com/valorisa/Claude-Skills). This is a transparent and standard distribution method for this type of tool.
  • [PROMPT_INJECTION]: The skill uses behavioral instructions to constrain the agent's actions, enforcing a plan-first approach and explicit confirmation gates. This is a safety-enhancing measure rather than a bypass of instructions.
  • [COMMAND_EXECUTION]: The skill allows the agent to run local test commands and utilize sub-agents for specific tasks. These actions are transparently defined within the development workflow and rely on the platform's native capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 08:43 PM
Security Audit — agent-trust-hub — spec-driven