codeguard-kotlin
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Kotlin source files and project configuration files to perform linting and formatting tasks using
./gradlew. This creates an attack surface where malicious instructions could be embedded in the code or configuration files to influence the agent's actions during execution. - Ingestion points: The agent reads source files (
.kt,.kts) and project metadata/build files (build.gradle,build.gradle.kts,settings.gradle,pom.xml) from the repository. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat file contents as strictly non-instructional data.
- Capability inventory: The skill utilizes shell execution capabilities to run
./gradlew detektand./gradlew ktlintFormat. - Sanitization: No sanitization or validation of the ingested file content or the resulting tool output is performed before it is processed by the agent.
Audit Metadata