skill-navigator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Prompt Injection (SAFE): The instructions establish a persona for the AI as a 'master skill navigator' to help organize workflows. There are no attempts to bypass safety guardrails or extract system prompts.
- Data Exposure & Exfiltration (SAFE): Analysis of the skill body shows no hardcoded credentials, access to sensitive local file paths, or outbound network requests.
- Remote Code Execution & Dependencies (SAFE): The skill does not include or install any third-party packages (Python/Node.js) and contains no commands for downloading or executing remote scripts.
- Indirect Prompt Injection (LOW): The skill processes user-provided descriptions of tasks to make recommendations. While this is an ingestion surface, the skill lacks dangerous capabilities (like file writing or network execution) that could be exploited by malicious data.
- Obfuscation (SAFE): All text is provided in clear markdown with no hidden characters, encoded strings, or homoglyph-based evasion techniques detected.
Audit Metadata