aws-cost-operations
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading external data from AWS logs and audit trails which is an inherent surface for indirect prompt injection. 1. Ingestion points: CloudWatch Logs and CloudTrail. 2. Boundary markers: Not defined. 3. Capability inventory: Querying AWS metrics and logs. 4. Sanitization: Not present.
Audit Metadata