configuring-imports
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a configuration reference for the Celigo platform. Analysis of all documentation and YAML schema files revealed no evidence of prompt injection, obfuscation, or unauthorized command execution.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill does not contain hardcoded credentials or sensitive file paths. It utilizes a connection management system (_connectionId) that abstracts credentials, and documentation explicitly advises against embedding secrets.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies surfaces for ingesting untrusted data through various adaptors (HTTP, RDBMS, AI). Ingestion points include API responses and database results. Capability inventory includes network operations, file system writes, and SQL execution. Boundary markers and sanitization are provided via documented input filters and guardrails (PII and moderation checks) in the GuardrailImport schema. Severity: LOW.
Audit Metadata