finalrun-generate-test
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of the 'finalrun check' CLI command to validate generated artifacts. This is a legitimate operation using the vendor's own tooling to ensure the correctness of test configurations.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its core function of reading and analyzing application source code. Ingestion points: Application source code files are read during Step 1 to infer app identity and functionality. Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent processes this external code. Capability inventory: The agent has the ability to write YAML files to the local file system and execute the 'finalrun' CLI tool. Sanitization: There are no explicit instructions to sanitize or validate the content of the source code before it influences the agent's generation logic or command-line parameters.
Audit Metadata