auth-tool-cloudbase
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest data from cloud API responses to inform subsequent configuration changes, creating a surface for indirect prompt injection. Ingestion points: Data returned from DescribeLoginStrategy and GetProviders in the SKILL.md templates. Boundary markers: None specified in the templates to separate data from instructions. Capability inventory: The skill uses callCloudApi to modify authentication providers, SMTP configurations, and OAuth credentials. Sanitization: No validation or sanitization of the ingested cloud data is described before it is reused in modification payloads.
Audit Metadata