kotlin-stable
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gradleand./gradlewcommand-line tools to execute compilation and test suites (e.g.,compileKotlin,test,check). This is the intended primary behavior for validating Kotlin code stability. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external project files and compiler error outputs. This represents an attack surface where malicious instructions hidden in code comments or logs could influence agent behavior. * Ingestion points: Kotlin source files and Gradle build output as described in
SKILL.md. * Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its own logic and data from external files. * Capability inventory: The skill has the capability to modify the filesystem and execute shell commands via Gradle. * Sanitization: There are no specific sanitization steps defined for handling external input data before processing.
Audit Metadata