kotlin-binary-compatibility

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project configuration files through a dedicated Python inspector script.
  • Ingestion points: The scripts/inspect-project.py script reads build.gradle, build.gradle.kts, settings.gradle, gradle.properties, and libs.versions.toml files from a user-specified root directory.
  • Boundary markers: The script filters content by extracting specific configuration keys and versions via regex and TOML parsing, avoiding raw text ingestion of the entire codebase.
  • Capability inventory: The skill is limited to read-only operations on project metadata and does not have network, file-write, or arbitrary command execution capabilities.
  • Sanitization: The inspection script outputs results in a structured JSON format, which prevents extracted project data from being misinterpreted as instructions by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill references established Kotlin documentation and development tools.
  • The documentation links point to official Kotlin sites (kotlinlang.org) and the official Kotlin GitHub repository.
  • These references are informational and do not involve untrusted third-party code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 05:02 PM