spec-driven

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a reference for project methodology and does not include any executable scripts or network-reaching code.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process documentation files from the specs/ directory (e.g., Vision.md, PRD.md, and tickets/). While these files could contain untrusted input if sourced from external contributors, the skill's primary function is documentation management and it does not possess capabilities (like network access or arbitrary command execution) that would make this injection path high risk.
  • [COMMAND_EXECUTION]: The skill suggests a command for the user to manually install complementary skills (npx skills add b12consulting/skills --skill <missing_skill>). This is an instruction for the user to perform setup and is not automatically executed by the agent. The resource specified (b12consulting/skills) belongs to the skill's author.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 06:26 PM