creating-secrets-using-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill allows for the acquisition of configuration parameters through external URLs and local file paths, which introduces a potential surface for indirect instructions to enter the agent's context.
- Ingestion points: The procedure in
references/create-secrets-using-best-practices.mdexplicitly supports input via a "URL: Link to configuration resources" and "File path." - Boundary markers: The skill does not define specific delimiters or explicit instructions for the agent to ignore potentially malicious embedded content within the retrieved configuration data.
- Capability inventory: The skill possesses the capability to execute AWS API calls (via
call_aws) to create secrets, KMS keys, and IAM policies, and it can perform diagnostic checks usingaws stscommands. - Sanitization: No specific sanitization or validation steps are outlined for the content fetched from external URLs before it is processed into secret configurations.
- Diagnostic Command Execution: The skill instructs the agent to verify the AWS CLI configuration using
aws sts get-caller-identity. This is a standard diagnostic practice for identity verification and does not pose a significant risk in this context. - Secret Handling Best Practices: The skill follows industry standards for secret management by enforcing KMS encryption with service-scoped policies, requiring least-privilege IAM roles, and prohibiting the logging or display of raw secret values in output.
Audit Metadata