ui-change-e2e
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute standard local testing commands (e.g.,
npm run test:e2e,pnpm test:e2e,playwright test). This is a standard and expected capability for a development-oriented agent. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing external data such as bug reports and project-specific test files. This represents a potential ingestion surface for untrusted content.
- Ingestion points: UI bug reports and existing E2E specification files (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: Execution of project-level shell commands for testing (SKILL.md).
- Sanitization: The skill does not explicitly mention sanitization of bug report content, but instructs the agent to translate the report into a failing test case, which is a structured activity.
Audit Metadata