sdd-plan
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
sddCLI for codebase analysis and documentation management, including commands likesdd doc stats,sdd doc search, andsdd doc complexity. - [COMMAND_EXECUTION]: The skill methodology involves creating JSON specification files that contain shell commands (e.g.,
npm test,npm run migrate) in themetadata.commandfield for automated verification tasks. - [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection (Category 8) as it analyzes untrusted codebase data to generate development plans; however, this is a standard characteristic of development tools and is managed through the structured planning workflow.
Audit Metadata