aws-cloudwatch
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from AWS CloudWatch Logs and CloudTrail Events, which is an inherent operational risk for any monitoring tool (indirect prompt injection surface).
- Ingestion points: SKILL.md (via log retrieval and audit trail lookup).
- Boundary markers: Absent.
- Capability inventory: AWS CLI and boto3 API calls.
- Sanitization: Absent.
- [COMMAND_EXECUTION]: Provides legitimate and expected AWS CLI commands for querying cloud infrastructure telemetry and logs.
Audit Metadata