enterprise-agent-shipper
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts external inputs such as agent blueprints and specification files to populate deployment templates. While this creates a surface for indirect prompt injection, the skill mitigates risk by using structured templates and focusing on generating configuration rather than executing untrusted data.
- [PRIVILEGE_ESCALATION]: The skill provides templates for generating IAM policies. It explicitly adheres to the principle of least privilege by including 'deny' blocks for high-risk permissions such as administrative access, deletion rights, and bulk data export.
Audit Metadata