111-java-maven-dependencies
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
./mvnw validateand./mvnw testto ensure project stability before and after making changes. These are standard Maven commands using the project's local wrapper script. - [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface related to untrusted data ingestion.
- Ingestion points: The project package name input by the user during the dependency selection flow in
SKILL.md. - Boundary markers: None; the input is requested and processed without specific delimiters.
- Capability inventory: The skill has the capability to modify project configuration files (
pom.xml,.mvn/jvm.config) and execute shell commands via the Maven wrapper. - Sanitization: No validation or sanitization is performed on the user-provided package name before it is interpolated into the
maven-compiler-pluginconfiguration as a compiler argument. While this represents a configuration injection surface, the impact is confined to the local build environment.
Audit Metadata