proj-gen-test
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user's project environment to perform its tasks.
- Ingestion points: The agent reads the project's
pom.xmlfile and source code files for Service and Controller layers (mentioned inSKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded content within the source files are provided.
- Capability inventory: The agent has the capability to modify the
pom.xmlfile and create new Java files in the project directory. - Sanitization: The instructions do not specify validation or sanitization of the content read from the project files before generating the test code.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to automatically modify the project's
pom.xmlfile if specific dependencies are missing, which involves file system write operations.
Audit Metadata