playwright-e2e-testing
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (scripts/generate_test_report.py and scripts/setup_test_env.py) to automate the initialization of test directories and the synthesis of E2E test artifacts into readable markdown reports. This execution of local code is a documented and functional component of the skill.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing content from arbitrary web pages.
- Ingestion points: Data enters the agent's context through DOM snapshots (browser_snapshot), console output (browser_console_messages), and network data (browser_network_requests).
- Boundary markers: The skill does not define specific delimiters or instructional boundaries to prevent the agent from potentially following directions embedded in the content of the tested application.
- Capability inventory: The agent has permissions to perform browser interactions, navigate to arbitrary URLs, and execute local report generation scripts.
- Sanitization: There is no evidence of filtering or sanitization of the content retrieved from web pages before it is analyzed by the agent or included in the final reports.
Audit Metadata