yq-yaml-processing
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate guidance for using a well-known, industry-standard tool (yq) for processing YAML data. It restricts the agent's tool access to a specific set of bash commands and file operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external YAML data such as Kubernetes manifests and GitHub Actions workflows. This presents an inherent surface for indirect prompt injection if the input files are attacker-controlled; however, the skill does not contain patterns that would lead to dangerous code execution.
- Ingestion points: The skill processes various external YAML files provided to the agent.
- Boundary markers: No explicit delimiter or "ignore instructions" markers are defined in the patterns.
- Capability inventory: Operations are limited to yq transformations and standard file access (Read, Write, Edit).
- Sanitization: No specific input sanitization is implemented, which is typical for informational utility skills.
Audit Metadata