devops
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security-first principles, specifically instructing the agent to use environment variables and secret stores instead of hardcoding sensitive information. It also includes a security checklist to verify that no secrets are committed to version control.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that involves reading project documentation and infrastructure configuration files. Ingestion points: .agent/rules/general-rules.md, docs/dev/[feature-name]/CONTEXT.md, and configuration files such as wrangler.toml, Dockerfile, and Terraform files. Boundary markers: Absent. Capability inventory: Command execution for environment setup and deployment. Sanitization: Absent. While this presents a surface for indirect prompt injection, it is a core requirement for a DevOps tool, and the skill includes internal security validation steps to mitigate risks.
Audit Metadata