cdk-construct-design-review
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to analyze Pull Request diffs, which are externally provided and potentially untrusted inputs. This represents a surface for indirect prompt injection, where instructions could be embedded within code or comments to influence the agent's behavior. This is a characteristic inherent to the skill's purpose as a reviewer.
- External Resource References: The skill directs the agent to reference documentation and design guidelines hosted on the official AWS CDK repository on GitHub. These references are used to verify design patterns against authoritative sources from a trusted organization.
- Secret Management Guidelines: The design rules include checks to ensure that sensitive data like passwords or tokens are handled using specific types (e.g.,
SecretValue). This is a documented design requirement aimed at preventing the accidental exposure of secrets in plaintext.
Audit Metadata