ln-42-acceptance-test-builder
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to identify and run shell commands defined within the local repository (e.g., native test runners, CI commands, and project generators). This execution is limited to the project-native tooling scope.
- [PROMPT_INJECTION]: The skill includes instructions to ingest and analyze untrusted content from the workspace, such as repository instructions, manifests, and CI configurations. This surface area is documented as a vector for potential indirect prompt injection from repository files.
- Ingestion points: Repository instructions, manifests, runner configuration, and CI files (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: Shell command execution, repository inspection, and file editing.
- Sanitization: None identified.
Audit Metadata