angular-architect
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The role definition and triggers are standard persona-setting instructions and do not contain bypasses or overrides of safety filters.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded secrets, or network operations were detected. The skill explicitly instructs against exposing sensitive data in client-side code.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No remote scripts are downloaded or executed. The listed 'references' are local markdown files commonly found within skill packages.
- [Indirect Prompt Injection] (LOW): The skill processes user-defined requirements to generate code. While this is an ingestion point for untrusted data, the skill lacks high-privilege capabilities such as automated file writing, system command execution, or network access, limiting the risk to the generated output only.
- [Dynamic Execution] (SAFE): No patterns of runtime code generation, compilation, or unsafe deserialization are present.
Audit Metadata