phoenix-channels-essentials

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and code snippets follow standard security practices for the Phoenix framework, such as using token-based authentication in connect/3 and performing authorization in join/3.\n- [INDIRECT_PROMPT_INJECTION]: The skill acknowledges and documents the surface for ingesting untrusted data via Phoenix Channels, providing explicit security rules to mitigate associated risks.\n
  • Ingestion points: The skill provides examples of handle_in/3 functions that receive untrusted payloads from clients in SKILL.md.\n
  • Boundary markers: The skill includes a mandatory rule (Rule 7) requiring that client payloads are never passed raw to the LLM context and should be validated against a strict schema.\n
  • Capability inventory: The provided logic includes broadcasting data to other users via broadcast! and sending messages to the client via push.\n
  • Sanitization: The skill demonstrates and recommends input sanitization techniques such as length limiting using String.slice and whitespace removal using String.trim.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 12:25 AM
Security Audit — agent-trust-hub — phoenix-channels-essentials