log-analytics

Warn

Audited by Snyk on May 8, 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 explicitly instructs the agent to fetch and sample documents from user OpenSearch indices (see "Sample Documents" / Phase 2 and the PPL query examples like source=<INDEX_PATTERN> | head 5 and the "Running PPL Queries" steps in log-analytics.md), meaning it ingests arbitrary user-generated/untrusted log content which can materially influence query construction and subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 8, 2026, 07:45 AM
Issues
1