shweshi/istio-mesh-zero-trust-audit
Audits Istio service meshes for evidence-backed Zero Trust maturity, attack paths, and remediation priorities.
90
90%
Does it follow best practices?
Impact
93%
1.19xAverage score across 4 eval scenarios
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow ingests live-cluster evidence via runtime command outputs and manifests (e.g., `kubectl get ... -o yaml`, `istioctl x describe pod`, traffic test results) which are outsider-authored free text from other parties’ Kubernetes resources and workloads, and this text is then used in the agent’s LLM context for analysis.
- Audited
- Security analysis