kubernetes-configmap-handler

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to handle Kubernetes ConfigMaps, which are external data sources that could contain malicious instructions.
  • Ingestion points: 'Read' and 'Grep' tools are authorized to process Kubernetes manifests.
  • Boundary markers: The skill lacks delimiters or instructions to ignore embedded commands within the processed data.
  • Capability inventory: High-privilege tools 'Bash', 'Write', and 'Edit' are enabled.
  • Sanitization: No input validation or content filtering is specified.
  • [Command Execution] (LOW): The skill requests 'Bash' tool access. While appropriate for a DevOps persona, the lack of input sanitization for the data processed via this tool poses a risk of executing commands derived from untrusted configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM