smoke-test
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes command-line instructions to start development servers and run tests in the terminal as part of its core functionality.
- [PROMPT_INJECTION]: There is a risk of indirect prompt injection when the agent processes data generated by the application being tested.
- Ingestion points: The skill ingests UI snapshots, interaction results, and command-line outputs (stdout/stderr) from the application under test.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat application output as untrusted data.
- Capability inventory: The agent can execute shell commands, automate browser interactions, and capture UI states.
- Sanitization: No sanitization, filtering, or validation is performed on the data captured from the application before it is presented to the agent for evaluation.
Audit Metadata