delphi
Warn
Audited by Snyk on Jul 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.delphi ingests the user-supplied question at runtime (delphi.py: reads
question/--question-file, then includes it in Wave 1 prompts and again in Wave 2 digest/revision prompts that are fed back into the LLM).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata