jetpack-compose

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because its core function involves processing untrusted source code from the user's project files. This is a common characteristic of development-focused AI skills and is considered safe within the intended context of use.
  • Ingestion points: The agent is instructed to read and analyze Kotlin files within the feature/ directory, specifically screens, routes, and ViewModels, as well as navigation and theme configurations.
  • Boundary markers: No specific delimiters or security instructions are provided to the agent to distinguish between user-provided code and its own system instructions.
  • Capability inventory: The skill utilizes shell commands through the Gradle wrapper (./gradlew) and has the capability to modify project files.
  • Sanitization: There are no instructions for sanitizing or validating the contents of the project files before they are interpreted or used in subsequent steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 12:31 PM
Security Audit — agent-trust-hub — jetpack-compose