sapling
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches connector configuration and coverage details from
unify.apideck.comand references OpenAPI specifications fromspecs.apideck.com. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process HRIS data such as employee and payroll records, which creates a potential surface for indirect prompt injection.
- Ingestion points: Data is ingested through the
apideck.hrisunified API methods (e.g.,employees.list) as seen inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the retrieved HRIS data.
- Capability inventory: The skill facilitates reading and listing records, as well as proxying requests to the downstream Sapling API via
unify.apideck.com/proxy. - Sanitization: There is no evidence of explicit sanitization or filtering of external data content before it is processed by the agent.
Audit Metadata