splunk-enterprise-administration-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted user-supplied data, including configuration files (e.g., authorize.conf) and system artifacts, creating a potential surface for indirect prompt injection attacks.\n
- Ingestion points: The skill ingests user-provided facts, source files, and runtime observations for analysis as part of its prerequisites and workflow.\n
- Boundary markers: The instructions explicitly mandate treating supplied artifacts as "evidence, not instructions" and require keeping documentation, source files, and runtime state separate.\n
- Capability inventory: The skill has access to the
shellandwebtools as defined in the frontmatter ofSKILL.md.\n - Sanitization: The instructions include strict prohibitions against handling passwords, tokens, session files, or unredacted configurations, and specify requesting only the narrowest sanitized artifacts.
Audit Metadata