helm-values-manager

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill is designed to manage and validate external Helm value files while possessing high-privilege capabilities, creating a significant attack surface.\n
  • Ingestion points: Helm YAML and JSON configuration files accessed via the Read tool.\n
  • Boundary markers: Absent. The skill instructions do not include delimiters or directives to ignore embedded instructions within processed data.\n
  • Capability inventory: Includes Bash (arbitrary subprocess execution), Write, and Edit (filesystem modification), which are available to the agent while processing external inputs.\n
  • Sanitization: None detected. There are no patterns for escaping, validating, or filtering external content before it is processed or used in shell commands.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:36 AM