aws-cost-operations
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains architectural documentation, operational workflows, and static CDK code snippets for CloudWatch alarms. No malicious scripts, unauthorized network operations, or credential exfiltration attempts were detected.- [PROMPT_INJECTION]: Analysis of the skill identifies an indirect prompt injection surface due to the ingestion of external AWS telemetry and logs. 1. Ingestion points: SKILL.md and operations-patterns.md describe tools and workflows for processing CloudTrail logs, CloudWatch logs, and billing reports. 2. Boundary markers: No delimiters or specific instructions for handling untrusted embedded content are present in the guidelines. 3. Capability inventory: Use of MCP servers for documentation searching, pricing calculation, and service health checks. 4. Sanitization: No sanitization or validation of the ingested external log data is specified. This exposure is consistent with the skill's primary purpose as a monitoring and auditing tool and is considered low risk.
Audit Metadata