The Agent Skills Directory

[Trusted External References]: The skill utilizes links to the official AWS CDK GitHub repository to provide the agent with authoritative testing guidelines. These references to well-known services and trusted organizations are used appropriately for context and do not introduce security risks.
[Indirect Prompt Injection Surface]: The skill is designed to process pull request diffs and file content, which constitutes an ingestion point for external data.
Ingestion points: Pull request diff content and file paths provided by the agent platform are the primary inputs for analysis.
Boundary markers: The skill does not explicitly define delimiters or instructions to ignore potential commands embedded within the diff content.
Capability inventory: The skill's scope is restricted to providing analysis and structured review comments. It does not utilize tools for network exfiltration, arbitrary command execution, or file system modification.
Sanitization: The instructions do not specify a mechanism for sanitizing or escaping the data retrieved from the diffs before processing.
[Static Analysis Logic]: The instructions guide the agent to perform a qualitative assessment of test coverage. This static evaluation does not involve the execution of the code under review, which aligns with secure practices for automated analysis tools.

cdk-testing-review