architecture-patterns
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a comprehensive knowledge base and validation system for software design, promoting best practices such as layer separation, dependency injection, and the AAA testing pattern.
- [PROMPT_INJECTION]: An indirect prompt injection surface was identified because the skill is configured to read untrusted external project files and has access to network-capable tools.
- Ingestion points: Source code files and project configurations (src/**, package.json, tsconfig.json) are ingested via Glob, Grep, and Read tools as defined in SKILL.md.
- Boundary markers: The skill reference files do not include specific delimiters or instructions to ignore potential commands embedded within the source code being analyzed.
- Capability inventory: The skill is permitted to use WebFetch and WebSearch tools (defined in SKILL.md), which creates a potential path for data exfiltration or unintended side effects if the agent obeys instructions hidden in analyzed code.
- Sanitization: No evidence of sanitization or validation of the ingested code content was found in the provided files.
Audit Metadata