aws-cost-optimization

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute AWS CLI commands for resource discovery and management. While these are legitimate administrative tasks, shell access represents an active capability surface.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of external AWS resource metadata.\n
  • Ingestion points: Data enters the agent context via CLI outputs (e.g., aws ec2 describe-instances, aws s3api list-buckets) that include user-controlled strings like resource tags, names, and descriptions.\n
  • Boundary markers: The skill does not define specific delimiters or instructional barriers to isolate untrusted CLI output from the agent's core logic.\n
  • Capability inventory: The skill has access to Bash, Read, and Write tools, providing a high-impact environment if an injection occurs.\n
  • Sanitization: There is no explicit sanitization or filtering of AWS API responses before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 07:01 PM
Security Audit — agent-trust-hub — aws-cost-optimization