skills/sakumyz/skills/test-generator/Gen Agent Trust Hub

test-generator

Fail

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: CRITICALPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill analyzes local source code and configuration files to generate test skeletons, creating an ingestion surface for untrusted data. 1. Ingestion points: package.json and target source files. 2. Boundary markers: None identified. 3. Capability inventory: File reading and code generation. 4. Sanitization: None.
  • Safe (SAFE): The automated scanner alert for 'wrapper.fi' is a false positive caused by the presence of 'wrapper.find()' in the code examples, which contains the flagged domain as a substring.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 20, 2026, 02:54 PM