browserstack

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package globally via npm. This is a primary tool provided by the vendor to manage the agent's environment.
  • [COMMAND_EXECUTION]: Executes various shell commands using the membrane CLI to authenticate, manage connections, and interact with the BrowserStack API.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from BrowserStack (such as test logs, build details, and project metadata) which could potentially contain untrusted content. 1. Ingestion points: Data is received via CLI commands like membrane action run and membrane request in SKILL.md. 2. Boundary markers: No explicit delimiters or warnings for the agent to ignore embedded instructions in the external data are present. 3. Capability inventory: The skill has capabilities to execute shell commands, perform network requests to the BrowserStack API, and modify BrowserStack resources in SKILL.md. 4. Sanitization: No specific sanitization or validation steps for the external data are documented in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 08:43 PM