content-ops
Warn
Audited by Snyk on Aug 19, 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). The workflow ingests outsider-authored free text from a user-provided atoms JSON (and uses it verbatim in Anthropic prompts for both draft generation and expert-panel scoring/revision), meaning the attacker controls the “SOURCE CONTENT” text that the LLM reads at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata