ln-42-acceptance-test-builder
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to run "repository-defined shell commands" and utilize project-native runners (CLI, API clients, etc.) to execute acceptance tests (SKILL.md).
- [DYNAMIC_EXECUTION]: The skill workflow involves creating, updating, and consolidating test scripts, fixtures, and helpers within the repository, which are then executed by the agent (SKILL.md, Section 3).
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Requirement documents, acceptance criteria, repository instructions, and external contract specifications are read from the workspace (SKILL.md, Section 1).
- Boundary markers: The instructions do not specify the use of delimiters or explicit "ignore embedded instructions" headers when processing external requirement files.
- Capability inventory: The skill possesses the capability to execute shell commands, perform file system operations (create/update/delete tests), and inspect repository state (SKILL.md, Sections 3 & 4).
- Sanitization: The skill includes a safety step to "Inspect the diff for... secrets, environment-specific paths, and changes outside the approved scope" (SKILL.md, Section 3), which serves as a manual review gate before finalizing changes.
Audit Metadata