gke-reliability
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading and describing Kubernetes resources, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill uses tools like
get_k8s_resourceanddescribe_k8s_resourceto fetch resource definitions (SKILL.md, sections 2 and 3). - Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions embedded within the fetched Kubernetes YAML content.
- Capability inventory: The agent is granted
apply_k8s_manifestcapability in the YAML frontmatter, allowing it to modify cluster state. - Sanitization: There is no evidence of sanitization or validation of the data retrieved from the cluster tools before the agent processes it.
Audit Metadata