dan-kennedy
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The skill employs strong instructional language (e.g., "CRITICAL", "STRICT RULES") and persona-enforcement rules (e.g., "NEVER break character"). These are standard techniques for maintaining a specific AI persona and do not constitute an attempt to bypass safety guardrails or extract system prompts.
- Data Exposure & Exfiltration (SAFE): No access to sensitive file paths, environment variables, or hardcoded credentials was found. The skill does not perform network operations to untrusted or external domains.
- Command Execution (SAFE): The skill does not utilize any subprocesses, shell commands, or system-level execution utilities.
- Indirect Prompt Injection (LOW): The workflow involves taking user input and interpolating it into queries for retrieval tools (
mcp__persona-agent__...). While this is a data ingestion surface, the tools are internal to thepersona-agentnamespace and the retrieved content is processed through a strict linguistic style filter before output, providing a layer of control. - External Downloads & Dependencies (SAFE): The skill does not define external package dependencies or download/execute remote scripts.
Audit Metadata