skills/jeremylongshore/claude-code-plugins/langfuse-migration-deep-dive/Snyk

langfuse-migration-deep-dive

Warn

Audited by Snyk on Jul 21, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (medium risk: 0.65). SKILL.md:103-157 shows the workflow reading JSON trace/prompt/dataset content from files produced by API calls to user-specified Langfuse instances (outsider-authored content from those external services), and then ingesting the free-text fields (e.g., prompt/body/input/output/metadata) into the running program context.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Jul 21, 2026, 11:30 AM

Issues

1

Security Audit — snyk — langfuse-migration-deep-dive