skills/accosine/dezbra/sdte-loop/Gen Agent Trust Hub

sdte-loop

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on a purely local, document-driven workflow for software development. It defines a structure for organizing project requirements and architecture within the repository's file system.
  • [COMMAND_EXECUTION]: The execution phase references pnpm run ok. This is a standard development command used to verify the state of a Node.js project. It does not involve arbitrary command execution or external network calls.
  • [INDIRECT_PROMPT_INJECTION]: The agent is instructed to read and follow directions from /specs/*.md files. While these files are external to the skill itself, they are part of the standard development context the agent is operating within. The skill provides clear boundaries and rules (S-1 to S-26) to manage this workflow securely.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:30 AM