browserstack
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
npx playwright testandnpm installto run cross-browser tests and manage thebrowserstack-localdependency, which is standard behavior for its intended purpose. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Reads local configuration files (
playwright.config.ts,package.json) and retrieves remote data viabrowserstack_get_logs,browserstack_get_session, and other MCP tools. - Boundary markers: The instructions lack explicit boundary markers or 'ignore' directives to prevent the agent from following instructions potentially embedded in external test logs.
- Capability inventory: The skill has the ability to write to files (
playwright.config.ts) and execute shell commands (npm,npx). - Sanitization: While it uses
encodeURIComponentto sanitize configuration data sent to BrowserStack, it does not specify sanitization steps for data retrieved from the service before it enters the agent's context.
Audit Metadata