cloudfront-distribution-setup
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to assist with CloudFront configurations by processing user requests and potentially reading local files. This capability, combined with the ability to write files and execute AWS CLI commands, creates a surface for indirect prompt injection.
- Ingestion points: User-provided requests and files read via the
Readtool. - Boundary markers: None identified; the skill lacks specific instructions to disregard instructions embedded within the processed data.
- Capability inventory:
Write,Edit, andBash(aws:*)tools allow for file modification and AWS command execution. - Sanitization: The skill does not define specific sanitization or validation routines for external inputs.
Audit Metadata