langsmith-fetch

Warn

Audited by Snyk on Mar 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly runs the langsmith-fetch CLI against LangSmith Studio (e.g., "langsmith-fetch trace " and "langsmith-fetch threads") to ingest and analyze traces/threads (user-generated third‑party content), which the agent is required to read and use to decide fixes and actions, so untrusted content could carry indirect prompt-instructions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 14, 2026, 01:50 PM
Issues
1