aws-cost-optimizer
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from AWS APIs, creating a potential surface for instructions embedded in resource tags or metadata to influence the agent. \n
- Ingestion points: Results from
aws ce get-cost-and-usage,aws ec2 describe-instances, andaws cloudwatch get-metric-statistics(SKILL.md). \n - Boundary markers: Includes an 'Analysis and change boundary' section instructing the agent to confirm the account, region, and dates. \n
- Capability inventory: Uses the
awsCLI to perform data analysis and suggests resource management actions (SKILL.md). \n - Sanitization: No explicit sanitization or filtering of API responses is documented. \n- [EXTERNAL_DOWNLOADS]: The skill references official AWS documentation and API guides for user reference. \n
- Evidence: Links to documentation on
aws.amazon.com(SKILL.md).
Audit Metadata