data-source-onboarding-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied requirements and data samples to provide advisory outcomes.
- Ingestion points: Requirements and sanitized event artifacts are provided by the user in workflow steps.
- Boundary markers: The skill requires the agent to label all information (Supplied, Documented, Inferred, Unknown) to maintain clear provenance.
- Capability inventory: The agent is restricted to web tool access for documentation lookup, with no file-writing or command execution capabilities enabled.
- Sanitization: Explicit constraints are provided in the Prerequisites section, prohibiting the request of credentials, tokens, certificates, or private events, and requiring the removal of sensitive details before event sharing.
- [EXTERNAL_DOWNLOADS]: The skill fetches data from official Splunk documentation domains using the web tool to validate product behavior and support claims. These resource targets are appropriate for the skill's purpose and trace back to the vendor's own infrastructure.
Audit Metadata