ai-agent-patterns

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill content. The skill provides code templates and architectural patterns for building LLM-powered workflows with durable execution.
  • [PROMPT_INJECTION]: The provided code examples demonstrate patterns for ingesting untrusted data (e.g., user questions, email content) directly into LLM prompts. While this is the intended purpose of the patterns, it represents an attack surface for indirect prompt injection in systems implemented using these templates.
  • Ingestion points: Input parameters such as text, question, article, and prompt in the script examples found in SKILL.md and references/streaming.md.
  • Boundary markers: Not present in the simplified documentation examples.
  • Capability inventory: The patterns utilize LLM text generation and task orchestration via the @trigger.dev/sdk.
  • Sanitization: No explicit sanitization or filtering of external content is demonstrated in the examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 03:06 AM
Security Audit — agent-trust-hub — ai-agent-patterns