mcp-playwright
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill facilitates processing of data from external, untrusted web environments. 1. Ingestion points: Web page content, console errors, and network logs from a reachable target environment. 2. Boundary markers: Absent; no instructions provided to distinguish web data from system instructions. 3. Capability inventory: Capture of screenshots and logs which are then processed by the agent. 4. Sanitization: None described in the skill definition.
- [No Code] (SAFE): No executable scripts, command-line arguments, or runtime code were found in the provided SKILL.md file.
Audit Metadata