bx-playwright-network
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of untrusted data from external sources, creating a surface for potential injection attacks.
- Ingestion points: The skill reads external data via
page.onConsole,page.onResponse,response.json(), andpage.visit()as documented inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to differentiate between untrusted external content and the agent's internal instructions.
- Capability inventory: The skill includes the ability to navigate to URLs, fill forms, execute HTTP POST requests, and persist session/storage state to the file system (e.g.,
ctx.saveStorageState("state.json")). - Sanitization: The instructions do not specify any validation, escaping, or sanitization protocols for data retrieved from web pages or API endpoints before it is consumed by the agent.
Audit Metadata