gsp-brand-sync
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill features a strong safety rule that prevents any brand modifications without explicit user confirmation after a report is presented.
- [COMMAND_EXECUTION]: Local shell tools like
bashandgrepare utilized for analyzing code and managing file structures within the project scope. - [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill processes unvalidated strings from the project codebase. Ingestion points: Project source files, style sheets, and user-facing copy analyzed in Step 1. Boundary markers: No delimiters or instructions are used to isolate project data from instructions. Capability inventory: The skill uses
Write,Edit, andBashtools. Sanitization: Ingested data is used directly for qualitative assessment without sanitization.
Audit Metadata