ln-635-test-isolation-auditor
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the target project's test suite. This execution is used to identify flaky tests, race conditions, and order-dependent failures by running tests multiple times or in randomized sequences. This is the primary intended functionality of the skill.
- [PROMPT_INJECTION]: The skill ingests external data from test files and metadata. This creates an indirect prompt injection surface; however, the skill's workflow focuses on pattern detection (using Grep) and monitoring test execution outcomes rather than interpreting natural language instructions from the analyzed files.
- Ingestion points: test files and testFilesMetadata (SKILL.md).
- Boundary markers: None explicitly defined.
- Capability inventory: Bash (test execution), Write (report output), Read/Grep/Glob (file analysis).
- Sanitization: No specific sanitization mentioned, as the skill performs structural analysis of the code.
Audit Metadata