ln-404-test-executor
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a test execution worker, which involves reading task descriptions and writing/executing test code. These behaviors are consistent with its stated purpose and the provided scripts manage runtime state safely within the project's .hex-skills directory.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted task descriptions from external providers.
- Ingestion points: Task descriptions fetched via getTask from Linear, GitHub, or local files (SKILL.md).
- Boundary markers: No explicit boundary markers or directives to disregard embedded instructions are present in the workflow.
- Capability inventory: The skill has access to Bash and mcp__hex-line__write_file (SKILL.md).
- Sanitization: Content from the task provider is used to guide test implementation without documented sanitization steps.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to run tests and execute shell commands defined in the project runbook. This functionality is the primary intended use case for the worker and is supported by internal runtime scripts.
Audit Metadata