function-creator

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The example function generateTaskSuggestion demonstrates an attack surface where untrusted user input is directly passed to an LLM. \n
  • Ingestion points: args.prompt in generateTaskSuggestion (SKILL.md)\n
  • Boundary markers: Absent\n
  • Capability inventory: External API call (OpenAI) and database write (ctx.runMutation) (SKILL.md)\n
  • Sanitization: Absent; input is directly interpolated into the message array.\n- [Data Exposure & Exfiltration] (SAFE): The skill demonstrates best practices for secret management by using environment variables (process.env.OPENAI_API_KEY, process.env.SENDGRID_API_KEY) rather than hardcoding credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 07:35 AM