aws-cdk-serverless-review
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (pull request diffs), which is a common attack surface for indirect prompt injection.
- Ingestion points: The skill retrieves the full diff of a Pull Request using Git/GitHub tools (SKILL.md, Paso 1).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the diff are specified.
- Capability inventory: The agent has the capability to publish consolidated findings back to the Pull Request as comments (SKILL.md, Paso 5).
- Sanitization: No specific sanitization or filtering of the diff content is mentioned before the analysis.
- [DATA_EXPOSURE]: The skill accesses codebase content through Git tools. This behavior is the primary intended function of the skill for performing code reviews and does not involve exfiltration to unauthorized domains.
- [EXTERNAL_DOWNLOADS]: The skill references official AWS documentation for best practices, which is a well-known and trusted source.
Audit Metadata