test
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a purely instructional workflow designed to guide an AI agent through testing tasks. It follows industry best practices for behavior-driven development (BDD) and test-driven development (TDD).
- [COMMAND_EXECUTION]: The skill instructs the agent to discover and execute existing repository commands for testing (e.g., runners like Vitest). This execution is limited to the local development environment's established scripts and tools, which is the primary intended purpose of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the local repository (manifests, lockfiles, scripts, and existing tests) to determine the testing environment. While this is a common attack surface for indirect prompt injection, the skill focuses on using the repository's own established infrastructure rather than arbitrary external inputs. Evidence chain:
- Ingestion points: Manifests, lockfiles, scripts, and nearby tests in the repository (SKILL.md, Step 2).
- Boundary markers: None explicitly present in the prompt templates.
- Capability inventory: Shell command execution for environment discovery and test running (SKILL.md, Step 2 and Step 6).
- Sanitization: Not explicitly present; the skill relies on the integrity of the repository's own configuration.
Audit Metadata