testing
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements several analysis commands (/unit-test-analyze, /integration-test-analyze, /testcase-analyze) that ingest untrusted user data—including source code, existing tests, and XLSX catalog exports—to generate testing strategies and proposals. * Ingestion points: Data enters the context via file reads or user input when analyzing code and test case catalogs (referenced in rules/testcase-testit-xlsx-read.md and SKILL.md). * Boundary markers: The instructions do not define explicit boundary markers or 'ignore embedded instructions' warnings for the data being analyzed. * Capability inventory: The skill directs the agent to generate textual reports and to 'Create a new file' for XLSX exports (specifically in rules/testcase-testit-xlsx-export.md). * Sanitization: No specific sanitization or escaping logic for the analyzed content is described in the instructions.
- [EXTERNAL_DOWNLOADS]: The skill references external dependencies and utilities for testing automation. * Evidence: References to @siberiacancode/playwright and @siberiacancode/testids are found in rules/integration-test-conventions.md and rules/integration-test-locator-testids.md. These represent resources owned by the skill author ('siberiacancode'). * Evidence: Mentions of well-known libraries such as vitest, @testing-library/react, and reactuse are present in metadata.json and reference files.
- [COMMAND_EXECUTION]: The instructions direct the agent to execute repository-specific verification and generation commands. * Evidence: rules/testcase-conventions.md instructs the agent to 'run the repository's own verification commands when feasible'. * Evidence: rules/integration-test-locator-testids.md instructs the agent to 'run the schema generator or validator'.
Audit Metadata