run-test-plan
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes arbitrary shell commands retrieved from a YAML test plan file, including setup scripts, build commands, background services, and individual test steps through Bash.
- [DYNAMIC_EXECUTION]: Shell commands are dynamically constructed and executed using Bash throughout the setup and test execution phases, based on strings provided in the external YAML input.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a YAML test plan that controls execution logic and command parameters, creating a vulnerability surface for indirect injection.
- Ingestion points: The YAML test plan loaded from the path specified by the
--planargument (defaulting todocs/testing/test-plan.yaml). - Boundary markers: No markers or instructions are used to delimit or ignore potentially malicious content within the YAML file.
- Capability inventory: Full shell command execution, network requests via
curl, file system writes todocs/testing/evidence/, and browser automation via theagent-browserCLI. - Sanitization: Although
yaml.safe_loadis used for parsing, no validation or sanitization is performed on the resulting command strings before execution.
Audit Metadata