aws-service-chaos-research
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
aws fis list-actionsandaws configure get regionto gather real-time data about available AWS fault injection capabilities in the user's specific region. These are read-only discovery commands used for the primary research purpose. - [EXTERNAL_DOWNLOADS]: The skill fetches content from official AWS documentation domains (docs.aws.amazon.com) using the
aws-knowledge-mcp-server. These references to a well-known service for documentation purposes are considered safe. - [DYNAMIC_EXECUTION]: While the skill instructions mention 'executing' a workflow, this refers to the agent's logical steps of searching and reading documentation, not the execution of arbitrary code or scripts.
- [SAFE]: The skill implements strict sequential execution and retry logic (10 retries with 5-second delays) for its MCP tool calls to respect rate limits and ensure stability. All gathered data is used to generate a local report file rather than being exfiltrated to third-party services.
Audit Metadata