observability-monitoring
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill includes examples that fetch and analyze arbitrary external URLs (e.g., references/distributed-tracing.md showing fetch_content using fetch_url(url) and SKILL.md's Langfuse analyze_content(url) / logs containing external "url" fields), so the agent could ingest and interpret untrusted, user-provided web content and be exposed to indirect prompt injection.
Audit Metadata