skills/openai/plugins/chat-sdk/Gen Agent Trust Hub

chat-sdk

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill provides patterns for ingesting and processing data from external messaging platforms (Slack, Discord, Telegram, etc.), which represents a potential surface for indirect prompt injection.
  • Ingestion points: Event handlers in SKILL.md (e.g., onNewMention, onSubscribedMessage) ingest message.text from users.
  • Boundary markers: The code examples do not include explicit delimiters or safety instructions to separate user input from system prompts.
  • Capability inventory: The skill uses tools to post messages (thread.post), stream AI responses (thread.stream), and manage thread state (thread.setState).
  • Sanitization: There are no explicit sanitization or validation steps shown for the ingested user content before it is processed by an AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:13 PM
Security Audit — agent-trust-hub — chat-sdk