langsmith-fetch
Warn
Audited by Snyk on Aug 14, 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.md describes fetching LangSmith execution traces from LangSmith Studio (e.g.,
langsmith-fetch traces ...andlangsmith-fetch trace <trace-id> ...) which contain arbitrary user/agent-generated free text submitted during agent runs, so an outsider can poison traces in a monitored/queried project/timeframe.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata