mobile-first-design-rules
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses structured tags such as , , and to define its persona as a coding standards expert. It includes 'Iron Laws' and 'Memory Protocols' that use strong language ('ALWAYS', 'NEVER', 'MANDATORY') to ensure the agent follows design guidelines. These are standard instructional techniques and do not attempt to bypass AI safety filters.
- [COMMAND_EXECUTION]: The SKILL.md file contains a memory protocol that instructs the agent to execute 'cat .claude/context/memory/learnings.md'. This command is used to retrieve localized context from the agent's expected environment and does not target sensitive system files.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface common to code-review tools.
- Ingestion points: Reads content from files matching glob patterns '**/*.{tsx,jsx}'.
- Boundary markers: No specific delimiters are defined in the skill to isolate untrusted code from instructions.
- Capability inventory: Requests 'Read', 'Write', and 'Edit' tools to interact with the filesystem.
- Sanitization: No content sanitization is implemented for the code being reviewed.
Audit Metadata