docs-lens-chart-settings
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill metadata and instructions direct the agent to fetch source code files from the official Elastic GitHub repository (
github.com/elastic/kibana). These references are appropriate for the skill's stated purpose of verifying UI documentation against implementation and target a well-known, trusted organization. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent reads and interprets external source code files using the
Read,Grep, andWebFetchtools. This constitutes a data ingestion surface for external content. - Ingestion points: Source code files from the
x-pack/platform/plugins/shared/lens/public/visualizations/directory in theelastic/kibanarepository. - Boundary markers: None explicitly defined in the prompt instructions to delimit code from instructions.
- Capability inventory: The agent's capabilities are limited to reading data (
Read,Grep,Glob,WebFetch). It lacks tools for command execution, file writing, or credential exfiltration. - Sanitization: None specified for the ingested content.
Audit Metadata