aws-cost-operations

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes official AWS CLI commands and designated MCP servers to achieve its stated goals of infrastructure monitoring and cost estimation. The resource usage is consistent with the skill's purpose and the developer's identity.
  • [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection because it ingests data from external sources such as CloudWatch logs and CloudTrail activity.
  • Ingestion points: Content is ingested from AWS logs and audit trails using mcp__cw__*, Bash(aws logs *), and Bash(aws cloudtrail *) as defined in SKILL.md.
  • Boundary markers: There are no explicit instructions to the agent to treat external log content as untrusted or to use specific delimiters.
  • Capability inventory: The skill is granted extensive access to AWS CLI functional areas including Cost Explorer, CloudWatch, Logs, Budgets, and CloudTrail via the Bash tool.
  • Sanitization: The skill does not implement validation or sanitization for the content retrieved from external logs or API activity records.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 09:26 AM