jetpack-compose

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No evidence of prompt injection, role-play bypasses, or instructions to ignore safety guidelines was found.
  • [SAFE]: No obfuscated content, such as Base64-encoded strings or hidden Unicode characters, was detected within the instructions or reference files.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use rg (ripgrep) to search the local filesystem for existing components (e.g., rg "@Composable" ui-kit). This is a legitimate and expected use of shell tools for a software engineering assistant to maintain code consistency and reuse.
  • [SAFE]: No hardcoded credentials, API keys, or sensitive file paths were identified. The instructions promote safe practices like hoisting state and avoiding passing ViewModels to reusable components.
  • [SAFE]: External URLs exclusively point to official Android developer documentation and Google's open-source repositories, which are recognized as trusted sources for development guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 12:31 PM
Security Audit — agent-trust-hub — jetpack-compose