security-review

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through the analysis of untrusted infrastructure-as-code files.
  • Ingestion points: Infrastructure files (Terraform, CloudFormation, SAM, CDK) read from the local environment as defined in the Review Process section of SKILL.md.
  • Boundary markers: Not present; there are no instructions to use specific delimiters or ignore embedded instructions within the ingested code files.
  • Capability inventory: The skill utilizes the AWS CLI (aws *), file system access (Read, Grep, Glob), and security scanners (checkov, tfsec, cfn-nag).
  • Sanitization: None identified; the instructions do not specify a validation or sanitization step for the content of the files being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 03:53 PM
Security Audit — agent-trust-hub — security-review