batch-executing-test-suites
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data including test suite configurations, source files, and test output (stack traces) to generate reports and fix recommendations.
- Ingestion points: Project configuration files, source code files, and the output (stdout/stderr) from test execution in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the data being processed by the
test_suite_runnersubagent. - Capability inventory: The
test_suite_runnersubagent hasenable_write_toolsset totrueand is instructed to execute shell commands to run tests. - Sanitization: There is no evidence of sanitizing or validating the content of stack traces or source files before they are parsed and used to generate diagnostic summaries.
- [COMMAND_EXECUTION]: The skill is designed to execute arbitrary shell commands specified as "test commands". While this is the primary intended purpose of the skill, it provides a mechanism for command execution that could be abused if the input commands are not strictly controlled.
Audit Metadata