websockets

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and broadcasting of real-time user data, which presents a surface for indirect prompt injection if malicious instructions are embedded in messages.
  • Ingestion points: WebSocket message handlers (e.g., chat:message event in SKILL.md) receive data directly from clients.
  • Boundary markers: The implementation examples lack explicit delimiters or instructions for the agent to ignore potentially malicious content within the message payloads.
  • Capability inventory: The examples focus on network-based event emission and do not include high-risk capabilities like system command execution or unauthorized file access.
  • Sanitization: While the references/PATTERNS.md file recommends input validation, the core examples in SKILL.md do not demonstrate specific sanitization or filtering of transmitted data strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:47 PM
Security Audit — agent-trust-hub — websockets