eg-enterprise

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the installation of Envoy Gateway components using the official Envoy Proxy OCI registry (oci://docker.io/envoyproxy/gateway-helm). This is a well-known and trusted technology source, and the reference is documented neutrally as a legitimate dependency for the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its interactive 'Intake Interview' workflow, which processes untrusted user input to generate Kubernetes manifests.
  • Ingestion points: User answers to deployment topology, compliance, and infrastructure questions in SKILL.md are used to populate configuration templates.
  • Boundary markers: Absent; the skill does not use specific delimiters or instructions to ignore embedded commands within user responses.
  • Capability inventory: The skill generates helm installation commands, kubectl verification commands, and complex Gateway API resource manifests (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the user's input strings is defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 08:46 PM