install-jdk-gradle
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project configuration files, creating a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Reads project files such as
gradle-wrapper.properties, Gradle configuration, and CI Java setup (referenced inSKILL.md). - Boundary markers: None; the skill does not specify delimiters or warnings to ignore instructions within the processed data.
- Capability inventory: Executes shell commands (
java -version,javac -version) and runs the project's Gradle wrapper (SKILL.md). - Sanitization: None; the skill does not specify validation or sanitization for the project data it reads.
Audit Metadata