cursor-run-smoke-tests
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect traces and logs to isolate root causes of test failures. This creates a surface where malicious instructions embedded in log output (produced by untrusted code or failed test cases) could influence the agent's behavior.
- Ingestion points:
SKILL.mdworkflows involve reading command-line output, traces, and log files. - Boundary markers: No explicit delimiters or instruction-ignore warnings are specified for the log analysis phase.
- Capability inventory: The skill enables shell command execution (
npm run) for building, running, and fixing code. - Sanitization: There is no evidence of sanitization or filtering applied to the logs before processing.
- [COMMAND_EXECUTION]: The skill defines a workflow requiring the execution of local build and test commands (e.g.,
npm run smoketest). While standard for development, users should be aware that the agent will execute these scripts within the repository context.
Audit Metadata