support-infrastructure-maintainer

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a Bash backup script and Terraform templates that perform system-level operations, including database dumps via pg_dump and archive creation using tar.
  • [DATA_EXFILTRATION]: The provided automation templates contain logic to transmit data to external services, specifically uploading backup archives to AWS S3 and sending status notifications to external webhooks via curl.
  • [PROMPT_INJECTION]: The agent's core function involves analyzing infrastructure health and performance data, which presents a surface for Indirect Prompt Injection.
  • Ingestion points: Assessment of infrastructure health and resource utilization metrics (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the analysis workflow.
  • Capability inventory: The agent can generate and recommend the execution of Bash scripts, Terraform configs, and Prometheus alerts.
  • Sanitization: There is no evidence of sanitization or validation of the metrics/logs before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 09:44 AM
Security Audit — agent-trust-hub — support-infrastructure-maintainer