splunk-indexes
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions specify the use of 'npx splunk-mcp', which involves downloading and executing a package from the npm registry at runtime.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Splunk indexes, creating a surface for indirect prompt injection where adversarial content in the data could influence agent behavior.
- Ingestion points: The 'get_indexes' tool retrieves data from external Splunk server indexes.
- Boundary markers: The skill does not define delimiters or instructions to ignore instructions embedded in the Splunk data.
- Capability inventory: The skill allows for index discovery and server configuration inspection via the 'splunk-mcp' server.
- Sanitization: No data sanitization or validation mechanisms are specified for the ingested Splunk content.
Audit Metadata