The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx splunk-mcp to download the latest version of an external tool from the NPM registry at runtime. This introduces a supply chain risk as the package is not version-pinned and originates from an unverified third-party author.
[REMOTE_CODE_EXECUTION]: Executing a package via npx constitutes remote code execution, as the agent environment fetches and runs code from an external repository to fulfill its server requirements.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface.
Ingestion points: Data retrieved from Splunk searches (logs and search metadata) via get_saved_searches and run_saved_search tools is directly incorporated into the agent's context.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat search result data as untrusted content.
Capability inventory: The skill allows listing and executing searches, which can return arbitrary data from the Splunk instance.
Sanitization: There is no evidence of filtering, escaping, or validation of the Splunk output before it is processed by the model.

splunk-saved