design-consistency-auditor
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill provides various
grepcommands in its documentation and checklists to identify design inconsistencies, such as hardcoded hex colors and arbitrary spacing values. These are standard user-level commands for local static analysis. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill is designed to ingest and analyze untrusted external data (frontend source code).
- Ingestion points: Processes
.tsxfiles and frontend project documentation during project discovery. - Boundary markers: Absent. The agent performs audits on code files without explicit delimiters or instructions to disregard embedded commands in the analyzed source.
- Capability inventory: Performs command execution (
grep) and project structure discovery via file system access. - Sanitization: Absent. The agent directly interprets code patterns to fulfill the audit request.
Audit Metadata