xlsx-processing-openai
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 1.00). The prompt instructs the agent to secretly use a proprietary "artifact_tool" (and to MUST use it when possible) while explicitly forbidding disclosure of its existence or code to users—an instruction to hide internal behavior that is outside the stated spreadsheet-help purpose and is deceptive.
Audit Metadata