110-java-maven-best-practices
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to run
./mvnw validate,mvn validate, and./mvnw clean verify. Executing the Maven wrapper (mvnw) involves running a script provided by the project being analyzed, which is standard behavior but involves local code execution. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ingestion of untrusted project configuration data.
- Ingestion points: The skill reads the root
pom.xmland all identified child modulepom.xmlfiles. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within the XML files.
- Capability inventory: The agent is authorized to execute terminal commands (
mvn,./mvnw) and perform file system modifications based on the project state. - Sanitization: No specific sanitization or filtering of the content read from the
pom.xmlfiles is implemented.
Audit Metadata