devops-infrastructure-engineer
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external third-party agent tools for automated verification and recovery, such as stablyai/orca@computer-use, midscene-skills@computer-automation, and codex-skills@gemini-computer-use. These represent dependencies on logic providers outside the skill's direct control.
- [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection by ingesting untrusted project data that influences high-privilege infrastructure outputs. • Ingestion points: Reads tech stack specifications and hosting requirements from .agents/startup_dna.md. • Boundary markers: Lacks explicit boundary markers or instructions to disregard instructions within processed project files. • Capability inventory: Generates CI/CD YAML configurations, Docker environment files, and IaC templates; utilizes computer-automation tools. • Sanitization: No evidence of input validation or sanitization for project-specific configurations.
Audit Metadata