sota-network-security

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit user-provided network configurations, Kubernetes manifests, and firewall policies. This ingestion of untrusted external data presents a theoretical attack surface where malicious instructions could be embedded in configuration files or comments to influence the agent's behavior during the audit process.
  • Ingestion points: The skill frequently instructs the agent to read and search through local files using grep and cat across all rules files (e.g., rules/02-segmentation-blast-radius.md, rules/03-k8s-network-policy.md).
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands within user files are defined.
  • Capability inventory: The skill utilizes powerful tools including kubectl, hubble, openssl, nmap, and curl to perform live connectivity tests and security verifications.
  • Sanitization: There is no evidence of sanitization or strict validation of the content of the files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 10:59 PM