elasticsearch-docs
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill's instructions, metadata, or reference files. The instructions focus on providing accurate technical documentation links.
- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion surface for external content from
elastic.co/docs. - Ingestion points: The agent is directed to search and read pages from the official Elasticsearch documentation site during execution (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters for separating user queries from retrieved documentation content, though it instructs the agent to read each page down to the relevant section.
- Capability inventory: The skill does not request or use any sensitive capabilities, such as file system access, shell execution, or external network requests beyond the documented search purpose.
- Sanitization: There are no explicit sanitization steps for the ingested documentation text.
- [EXTERNAL_DOWNLOADS]: The skill references the official Elasticsearch documentation site (
elastic.co/docs) as a primary source for grounding and source linking. This is a well-known service and the reference is for informational purposes.
Audit Metadata