splunk-dashboard-converter

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires the agent to receive user-provided Simple XML and "preserve SPL exactly" and place original element text/attribute values (including queries) verbatim into the returned Studio JSON, which means any secrets contained in the input would be copied into the output.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). SKILL.md Phase 2 “Verify the input” and subsequent steps ingest the classic Simple XML source provided by the caller (including untrusted element text/attribute values/comments/SPL queries) directly for conversion planning and JSON generation, so outsider-authored free text can be submitted into that input.