ptlam-code-style-kotlin
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and analyzing repository configuration and source files (e.g., build.gradle, Kotlin source files). This is a standard surface for indirect prompt injection, where malicious instructions could be embedded in data files, but it is necessary for the skill's primary function of code style enforcement.
- Ingestion points: Repository files including Gradle build scripts and Kotlin sources.
- Capability inventory: Execution of local Gradle tasks and modification of source files.
- Boundary markers: None explicitly mentioned.
- Sanitization: No sanitization of code content is defined.
- [COMMAND_EXECUTION]: The skill utilizes standard Gradle commands for linting and testing (e.g.,
./gradlew detekt,./gradlew ktlintCheck). These are expected behaviors for a development-focused skill and do not involve unauthorized or elevated privileges.
Audit Metadata