gradle-kotlin-dsl-doctor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted build data which exposes a surface for indirect instructions to influence agent behavior.
- Ingestion points: The skill reads files including build.gradle.kts, settings.gradle.kts, gradle.properties, and version catalogs as specified in the 'Read First' section of SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions that might be embedded within the project files.
- Capability inventory: The skill uses commands like ./gradlew build and ./gradlew dependencies which can execute arbitrary code defined in the build scripts.
- Sanitization: The skill does not define methods for sanitizing or validating the content of the ingested files before processing.
- [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with the build system.
- Evidence: The 'High-Signal Commands' section in SKILL.md explicitly lists the use of ./gradlew for help, build, and dependency analysis, which are necessary for the skill's diagnostic purpose.
Audit Metadata