playwright-debugging
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard Playwright CLI commands such as
npx playwright testandnpx playwright show-report. these operations are restricted to the local environment and are intended for running and reviewing the output of end-to-end tests. - [PROMPT_INJECTION]: The skill includes instructions for the agent to read test failure artifacts like
error-context.md. This represents a potential surface for indirect prompt injection if the web application being tested outputs malicious content designed to influence the agent's behavior. - Ingestion points: The file
test-results/<test-name>/error-context.mdis specified as a source for page structure context. - Boundary markers: Not explicitly implemented in the instructions; the content is described as YAML within markdown.
- Capability inventory: The skill has the capability to execute shell commands via the Playwright CLI.
- Sanitization: No specific sanitization or filtering logic is provided for the error context content.
Audit Metadata