docs-check-contradictions
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from local documentation files and external web pages, creating a potential surface for indirect prompt injection.
- Ingestion points: The agent reads Markdown files provided in the
$ARGUMENTSpath and fetches published documentation from the Elastic Docs MCP server or viaWebFetchfromelastic.coURLs. - Boundary markers: The instructions do not implement specific delimiters or 'ignore' instructions when processing external content to prevent the LLM from following commands embedded in the docs.
- Capability inventory: The skill utilizes
Read,Grep, andGlobfor filesystem access andWebFetchfor network operations. It does not possess file-write or shell execution capabilities. - Sanitization: No sanitization or validation of the retrieved text content is performed before it is processed for claim extraction.
- [EXTERNAL_DOWNLOADS]: The skill retrieves documentation content from
https://www.elastic.co/docs/_mcp/and other official Elastic documentation URLs. These references target the vendor's own infrastructure and are used for their intended purpose of documentation consistency verification.
Audit Metadata