mobile-ux-patterns
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes external, untrusted codebase files and configurations to generate UX compliance reports.
- Ingestion points: Phase 1 through Phase 7 involve reading various source code and configuration files.
- Boundary markers: Not present.
- Capability inventory: The skill has the capability to read project files and write to a local telemetry log.
- Sanitization: No sanitization or escaping of ingested content is defined in the instructions.
- [DATA_EXFILTRATION]: The skill includes a 'Self-Evolution Telemetry' mechanism that accesses the
~/.claude/projects/hidden directory to append execution metadata. This directory contains platform-specific project information and history. While the telemetry is intended for local self-improvement of the skill, it represents a form of tracking that interacts with sensitive hidden paths.
Audit Metadata