elasticsearch-logs

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a Docker image hosted on the official Elastic container registry (docker.elastic.co/mcp/elasticsearch). This is a well-known service and the use of digest pinning is a recognized security best practice to ensure supply chain integrity.\n- [PROMPT_INJECTION]: The skill ingests untrusted log data (such as syslog, application logs, or Zeek exports) from Elasticsearch indices, which establishes a surface for indirect prompt injection. If log entries contain adversarial instructions, they could potentially influence the agent's analysis.\n
  • Ingestion points: Untrusted data enters the agent context via the search and esql tools.\n
  • Boundary markers: The instructions do not specify the use of delimiters or boundary markers to separate log content from the agent's prompt context.\n
  • Capability inventory: The skill's capabilities are limited to read-only metadata and document retrieval tools (list_indices, get_mappings, search, esql, get_shards). It does not have the ability to write files, execute arbitrary local commands, or perform unmanaged network operations.\n
  • Sanitization: There is no mention of content sanitization or filtering for the retrieved log data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:47 AM
Security Audit — agent-trust-hub — elasticsearch-logs