kotlin-code-style

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process, review, and modify Kotlin source code, which serves as an ingestion surface for untrusted data. Malicious instructions could be embedded within code comments or metadata of the files being analyzed.
  • Ingestion points: Kotlin source files and build configurations processed during code review or formatting tasks.
  • Boundary markers: Absent. The instructions do not define specific delimiters or warnings to ignore instructions embedded within the processed code.
  • Capability inventory: The skill has the capability to execute shell commands for build tasks and formatting tools.
  • Sanitization: Absent. The skill does not specify any sanitization or validation of the content within the Kotlin files before processing them.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard development tools to verify and format code.
  • Evidence: Instructions include running ktlintFormat and ktlintCheck via the command line.
  • Evidence: Mentions modifying environment variables like GRADLE_USER_HOME and running Gradle tasks for verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 06:17 AM
Security Audit — agent-trust-hub — kotlin-code-style