argocd-app-deployer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to process potentially untrusted external data (Kubernetes manifests, ArgoCD configurations, and Terraform files) while having access to powerful system tools.
  • Ingestion points: Processes user-provided DevOps patterns and infrastructure files via Read/Grep tools.
  • Boundary markers: None specified to delimit untrusted content from system instructions.
  • Capability inventory: Includes high-impact tools: Bash, Write, and Edit.
  • Sanitization: No explicit sanitization or validation of the ingested content is defined in the skill manifest.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM