yq-yaml-processing

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted YAML data from various sources.\n
  • Ingestion points: The skill reads and transforms external configuration files including Kubernetes manifests (deployment.yaml), GitHub Actions workflows (.github/workflows/*.yml), and Helm charts (values.yaml).\n
  • Boundary markers: There are no instructions to use delimiters or ignore instructions that might be embedded within the YAML files being processed.\n
  • Capability inventory: The skill utilizes tools like 'Bash(yq *)', 'Write', and 'Edit', allowing it to modify system configurations based on processed data.\n
  • Sanitization: The skill does not implement or suggest sanitization or validation of the YAML content to prevent the execution of instructions contained within the data fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 09:10 AM