gcp-artifact-registry
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates management of Google Cloud Platform (GCP) Artifact Registry using official gcloud CLI commands. Analysis found no malicious patterns such as data exfiltration to unauthorized domains, code obfuscation, or privilege escalation.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external GCP resource metadata (such as repository names, image tags, and vulnerability reports). While this data is technically untrusted, the skill employs structured JSON formatting (
--format=json) and usesjqfor parsing and filtering, which reduces the surface area for instruction injection compared to raw text processing. This is a common property of cloud management skills and is considered low risk.
Audit Metadata