devops-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that combines external data ingestion with powerful infrastructure management tools, creating an indirect prompt injection surface.
- Ingestion points: The instructions mandate the use of
mcp__context7__query-docs,WebSearch, andWebFetchto retrieve technical specifications and community guidance from external, potentially untrusted web sources (SKILL.md, references/terraform.md). - Boundary markers: The skill lacks explicit boundary markers or instructions that would prevent the agent from being influenced by malicious commands embedded in the fetched documentation.
- Capability inventory: The skill provides guidance for using highly capable tools including Terraform/OpenTofu for infrastructure provisioning, Kubernetes for container orchestration, and GitHub Actions/Jenkins for CI/CD pipelines.
- Sanitization: There are no requirements for the agent to sanitize or validate external content before using it to generate infrastructure manifests or execute deployment commands.
Audit Metadata