compose-agent

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of legitimate technical documentation for Android development. All provided instructions and code examples adhere to official AndroidX and Kotlin standards.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to analyze and modify external Android project code. However, the skill instructions are focused on correctness and developer safety rather than exploitation. 1. Ingestion points: The skill uses Read, Glob, and Grep tools to access source files. 2. Boundary markers: No explicit boundary markers are used to delimit external content. 3. Capability inventory: The skill has Edit, Write, and Bash capabilities for project modification. 4. Sanitization: No specific sanitization methods for external code are mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:09 AM