sdd-design
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill is restricted to reading project files and writing markdown documentation. It does not contain any instructions for executing shell commands, system binaries, or administrative tasks.- [DATA_EXPOSURE]: While the skill reads sensitive project context such as architecture decisions and tech stacks, this access is scoped to local file system reads necessary for its documented purpose. There are no network operations or external endpoints involved in the process.- [REMOTE_CODE_EXECUTION]: The skill does not download external scripts or packages. It explicitly states that it does not write implementation code, focusing solely on technical design documentation.- [PROMPT_INJECTION]: The instructions do not contain any patterns aimed at bypassing AI safety guardrails, overriding system prompts, or extracting internal instructions.
Audit Metadata