luigi-task-generator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is intended for data pipeline orchestration and requests powerful tools (Bash, Write, Edit, Grep, Read), which constitutes an indirect prompt injection surface. Evidence: (1) Ingestion points: User requests and data processed via the Read tool. (2) Boundary markers: Absent; no delimiters or instructions to ignore embedded commands are provided. (3) Capability inventory: Bash, Write, Edit, Grep, Read. (4) Sanitization: Absent; no input validation or sanitization logic is defined.
  • [Safe] (SAFE): The skill consists solely of metadata and documentation; no executable scripts, hardcoded credentials, or obfuscated payloads were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM