mcp-playwright

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill utilizes the microsoft/playwright-mcp server. According to the [TRUST-SCOPE-RULE], dependencies from the 'microsoft' organization are considered trusted, downgrading this finding from MEDIUM to LOW.
  • [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8c: Tool output poisoning). An attacker could place malicious instructions on a website that the agent visits using this skill.
  • Ingestion points: The skill retrieves and processes untrusted data from external URLs via browser navigation as described in SKILL.md prompt templates.
  • Boundary markers: No boundary markers or 'ignore' instructions are defined to separate web content from agent instructions.
  • Capability inventory: The skill allows browser-driven verification, DOM access, and screenshot capture, which can be leveraged if the agent obeys instructions found on a page.
  • Sanitization: No sanitization or validation of the external content is performed before it is added to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 08:57 PM