skills/ramziddin/ccplugins/websockets/Gen Agent Trust Hub

websockets

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by demonstrating the processing of data from WebSocket clients.
  • Ingestion points: Untrusted data enters the application through the @MessageBody() decorator in Gateway methods within SKILL.md.
  • Boundary markers: The provided example implementations do not include delimiters or boundary markers to separate untrusted data from instructions.
  • Capability inventory: The code snippets show basic event handling and broadcasting but do not implement dangerous capabilities such as shell execution or file system operations.
  • Sanitization: No data sanitization or validation logic is present in the connectivity-focused examples.
  • [SAFE]: The documentation includes WebSocket configuration examples using a CORS wildcard (origin: '*'). This is a best practice violation for production environments as it allows connections from any origin, but it is a standard pattern for educational templates to ensure connectivity works during initial development.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 08:42 AM