aws-health-check

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool, explicitly restricted to aws CLI commands, to perform diagnostic checks on AWS infrastructure. This includes querying identity (sts get-caller-identity), S3 public access blocks, security group rules, RDS instance accessibility, and EC2 metadata options.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes data from AWS resource metadata (such as bucket names or instance tags) which is then used to generate a report. Ingestion points: AWS CLI output for S3, EC2, and RDS resources (SKILL.md). Boundary markers: Absent. Capability inventory: aws CLI read access via Bash (SKILL.md). Sanitization: None detected. This is considered low risk given the read-only auditing purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 03:53 PM
Security Audit — agent-trust-hub — aws-health-check