langsmith-fetch

Warn

Audited by Snyk on Mar 15, 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 core workflows in SKILL.md and README explicitly instruct the agent to run langsmith-fetch against LangSmith Studio (e.g., "langsmith-fetch traces" and "langsmith-fetch threads") to fetch and analyze execution traces and conversation threads (user-generated/untrusted content) which the agent then reads and uses to drive analysis and suggested fixes, so external content can influence tool use and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 10:43 PM
Issues
1