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
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:56 AM