devops-engineer

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to extend its capabilities by installing Model Context Protocol (MCP) servers. It references several packages to be installed via npx, including @modelcontextprotocol/server-github, @microsoft/azure-devops-mcp-server, and a community-maintained package @ibraheem4/linear-mcp.
  • [COMMAND_EXECUTION]: The instructions frequently guide the agent or user to execute shell commands using common DevOps CLI tools like terraform, kubectl, docker, and platform CLIs (gh, glab, az) to manage infrastructure and pipelines.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because its primary function involve ingesting untrusted data from external sources.
  • Ingestion points: Reads workflow run logs, PR checks, deployment statuses, and incident tickets (documented in references/integrations.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided templates.
  • Capability inventory: The skill has extensive command execution capabilities across all reference files, including managing cloud resources and CI/CD pipelines.
  • Sanitization: There are no explicit instructions for sanitizing or validating the content of external logs or deployment data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — devops-engineer