eks-operation-review
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection Surface]: The skill is designed to ingest and analyze untrusted data from external sources, which could potentially contain embedded instructions.
- Ingestion points: The skill collects data from Kubernetes API resources, Pod logs (
pods_log), CloudWatch logs, and CloudTrail events, as detailed inSKILL.md(Step 2 and 3). - Capability inventory: The agent possesses extensive read capabilities across the Kubernetes and AWS environments (
resources_list,events_list, various AWS APIs) and the ability to generate file artifacts (eks-review-*.md). - Boundary markers: The instructions in
SKILL.mddo not currently define explicit boundary markers or instructions to ignore potential commands embedded within the logs or resource metadata being analyzed. - Sanitization: There is no explicit mention of sanitization or filtering for the external content before it is processed for the report generation.
Audit Metadata