400-frameworks-quarkus-create-project
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 several shell commands to manage SDKs and build the project. These include
sdk version,sdk install java,quarkus create app, and./mvnw clean verify. While these are standard developer workflows, they involve executing code on the local system. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where user-supplied inputs (group ID, artifact ID, package name, extensions) are directly interpolated into shell commands, such as
quarkus create app <group>:<artifact>:<version>. This creates a surface for command injection if a user provides malicious input containing shell metacharacters. - Ingestion points: User-provided project coordinates and extension names gathered in Step 1 of the reference file.
- Boundary markers: Absent; the instructions do not specify delimiters or warnings for the agent to ignore instructions embedded in these inputs.
- Capability inventory: File system modification and shell command execution via
sdk,quarkus, andmvnw(Steps 2 through 5 in the reference file). - Sanitization: Absent; there are no instructions provided to validate or sanitize the user-supplied strings before they are used in commands.
Audit Metadata