Skills
skills/jnpiyush/agentx/ai-agent-development/Gen Agent Trust Hub

ai-agent-development

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements patterns for processing external datasets and user queries that are susceptible to indirect prompt injection.
  • Ingestion points: scripts/run-model-comparison.py ingest data from JSONL files, and the generated agent code in scripts/scaffold-agent.py processes queries from environment variables.
  • Boundary markers: The generated system prompts lack explicit delimiters or instructions to ignore instructions within user data.
  • Capability inventory: The skill enables LLM-driven actions via the Microsoft Agent Framework.
  • Sanitization: While the scripts/validate-agent-checklist.ps1 tool checks for input validation, the generated scaffolding does not include sanitization logic by default.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 01:56 PM