kubernetes-secrets-manager

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill enables the Bash tool for DevOps tasks. This powerful capability is appropriate for the primary purpose of managing infrastructure but increases the risk if the agent is leveraged for unintended command execution.
  • PROMPT_INJECTION (LOW): The skill provides an attack surface for Indirect Prompt Injection (Category 8) by processing external data using a high-privilege toolset.
  • Ingestion points: External Kubernetes manifests and user-provided configuration requests (SKILL.md).
  • Boundary markers: Absent; the skill does not define specific delimiters to isolate untrusted data from the agent's instructions.
  • Capability inventory: Includes Bash, Read, Write, Edit, and Grep tools (SKILL.md).
  • Sanitization: Absent; there are no instructions for the agent to validate or sanitize external manifests before execution or modification.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:07 PM