istio-traffic-management
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides several YAML templates for Kubernetes resources that interpolate values like hostnames, labels, and header names. If these values are sourced from untrusted external data, they could be used to inject malicious configuration or override agent behavior.
- Ingestion points: The skill ingests user-provided inputs for fields such as
hosts,subsets,labels, andhttpHeaderNameacross various YAML templates inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions telling the agent to ignore embedded commands within the interpolated data.
- Capability inventory: The skill includes shell capabilities via
istioctlcommands for analyzing configurations and viewing proxy logs. - Sanitization: No sanitization, validation, or escaping logic is provided for the data used to populate the templates.
Audit Metadata