e2e
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to interact with external web content.
- Ingestion points: Web content and external data ingested via the BrowserOS interface.
- Boundary markers: None explicitly defined within the prompt structure.
- Capability inventory: Terminal execution via the ExecutionProxy Interface and file system write access for saving test results and markdown artifacts.
- Sanitization: The skill contains explicit instructions to treat external data as hostile and to redact secrets and PII before sharing context with subagents.
- [COMMAND_EXECUTION]: The skill executes terminal commands through a defined ExecutionProxy Interface (using the 'rtk' prefix) to perform testing tasks such as 'npm test'. This is consistent with the stated purpose of an end-to-end testing specialist.
Audit Metadata