prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file access, or network operations were found.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not define any dependencies (Python or Node.js) and does not attempt to download or execute remote scripts.
- [Indirect Prompt Injection] (SAFE): The skill provides templates that interpolate untrusted data (e.g.,
{text},{code},{user_input}). While these are ingestion points for external data and lack boundary markers or sanitization, the skill possesses no executable capabilities (tools, subprocesses, or network calls), making the injection surface non-exploitable. - [No Code] (SAFE): The entire skill consists of markdown-based instructions and prompt templates without any accompanying scripts or binary files.
Audit Metadata