support-infrastructure-maintainer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves assessing infrastructure health and performance metrics, which are ingestion points for external, potentially untrusted data. Since the agent is also tasked with generating infrastructure configurations and maintenance scripts, there is a risk that malicious data (e.g., poisoned log entries) could influence the generated output. \n
- Ingestion points: System health metrics and performance data mentioned in the Infrastructure Assessment and Planning section of SKILL.md. \n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided. \n
- Capability inventory: Generation of Terraform configurations, Prometheus rules, and Bash scripts as described in the Infrastructure Management Deliverables section. \n
- Sanitization: No explicit sanitization or validation of the input metrics or logs is mentioned. \n- [DYNAMIC_EXECUTION]: The skill provides detailed templates for generating executable Bash scripts and Infrastructure-as-Code (Terraform) configurations to manage system operations. While these are based on static templates provided in the skill instructions, the agent's capability to modify and deploy these scripts at runtime is a risk factor that requires human oversight.
Audit Metadata