accessibility-check
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by navigating to and processing data from user-supplied external URLs.
- Ingestion points: Untrusted data enters the agent context through the use of
mcp__playwright__browser_navigateandmcp__playwright__browser_snapshotinSKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the processed web content.
- Capability inventory: The skill utilizes Playwright MCP tools to interact with web browsers.
- Sanitization: There is no evidence of validation or sanitization of the content retrieved from external sites.
Audit Metadata