churn-prevention
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as search results, web scraping, and model inference via the
sandbase_runtool. - Ingestion points: External evidence, search results, and enrichment data retrieved via the SandBase API as described in
SKILL.mdandreferences/sandbase-api-map.md. - Boundary markers: The instructions do not specify the use of delimiters or explicit boundary markers to wrap untrusted data, though it requires user confirmation for the call execution itself.
- Capability inventory: The skill possesses the capability to execute external API calls and search/scraping tasks via
sandbase_run. - Sanitization: The skill instructions mention using 'schema-defined arguments' for the
sandbase_runtool, which provides a layer of structured data validation, though it does not explicitly describe content sanitization for the data returned from those tools.
Audit Metadata