backend-design-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is intended to process external design artifacts like API specifications, database schemas, and ADRs. This presents a surface for indirect prompt injection where malicious instructions could be embedded in the documentation being reviewed. 1. Ingestion points: External architectural data and documents mentioned in
SKILL.md. 2. Boundary markers: None specified in the instructions to isolate untrusted data. 3. Capability inventory: No executable scripts, subprocess calls, or network operations; functionality is limited to text analysis and report generation. 4. Sanitization: No sanitization or validation logic is present for incoming data. - [No Code] (SAFE): The skill is entirely composed of documentation and templates. No scripts (.py, .js, .sh), binaries, or configuration files that trigger command execution were found.
Audit Metadata