azure-playwright-workspaces
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch technical documentation from
learn.microsoft.com. It also includes a reference to the officialMicrosoftDocs/mcpGitHub repository for installation instructions. These external references target well-known, trusted service domains and organizations. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from external documentation sources, creating a potential surface for indirect prompt injection.
- Ingestion points: External documentation fetched from
learn.microsoft.comas described inSKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the fetched content.
- Capability inventory: The skill is scoped to documentation retrieval and does not utilize dangerous capabilities such as arbitrary command execution, network exfiltration of sensitive data, or file system writes.
- Sanitization: The skill does not explicitly define sanitization or validation rules for the fetched Markdown content.
- [SAFE]: Analysis of the skill instructions, metadata, and scripts revealed no evidence of malicious behavior. There are no attempts at obfuscation, credential theft, or privilege escalation. The skill's functions are entirely consistent with its stated purpose of assisting with Playwright Workspaces development.
Audit Metadata