411-frameworks-quarkus-jdbc
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands including
./mvnw compile,mvn compile,./mvnw clean verify, andmvn clean verifyto validate code changes (SKILL.md, references/411-frameworks-quarkus-jdbc.md). - [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection due to the combination of project file ingestion and shell execution capabilities.
- Ingestion points: The agent reads and analyzes existing project source code and build configuration files (SKILL.md, references/411-frameworks-quarkus-jdbc.md).
- Boundary markers: The instructions do not define explicit delimiters to separate skill instructions from the project data being processed.
- Capability inventory: The skill utilizes build tool commands (
mvnw,mvn) which could be manipulated if a project file contains malicious scripts (e.g., a modified Maven Wrapper). - Sanitization: The process does not specify validation or sanitization of the external project code before it is used to inform agent actions or build processes.
Audit Metadata