websocket-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external WebSocket event payloads and message contracts, which introduces a potential attack surface for indirect prompt injection.
- Ingestion points: Real-time WebSocket event payloads and message contracts described in the working mode (SKILL.md).
- Capability inventory: The skill metadata includes
sandbox_mode: workspace-write, allowing the agent to modify files in the environment (SKILL.md). - Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore instructions that might be embedded in the WebSocket data.
- Sanitization: There are no instructions for sanitizing or filtering the content of the payloads to prevent the execution of malicious instructions found within the data stream.
Audit Metadata