aws-cloud-monitoring
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the
cloudwatch-mcp-serverpackage from AWS Labs. - [COMMAND_EXECUTION]: Executes the
uvxcommand to run theawslabs.cloudwatch-mcp-serverat runtime. This is standard behavior for utilizing MCP servers to interface with AWS APIs. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, specifically AWS CloudWatch Logs and Metrics.
- Ingestion points: Data enters the agent context through CloudWatch metric queries and Logs Insights query results (referenced in SKILL.md).
- Boundary markers: None explicitly defined in the provided instructions to separate external log content from agent instructions.
- Capability inventory: The skill uses the MCP server to perform AWS API calls including
DescribeAlarms,GetMetricData, andStartQuery(Logs Insights). - Sanitization: No specific sanitization or filtering of log/metric content is described before processing by the agent.
Audit Metadata