clinical-guideline-navigator
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill definition is purely instructional and does not contain executable scripts or dangerous commands.
- [PROMPT_INJECTION]: The instructions focus entirely on providing guideline-concordant medical information. There are no attempts to bypass safety filters, extract system prompts, or override agent constraints.
- [DATA_EXFILTRATION]: There is no evidence of commands or logic that access sensitive local files (e.g., SSH keys, credentials) or transmit user data to external servers.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute remote code. The installation command provided in the documentation refers to the author's own repository, which is a standard distribution method for this type of tool.
- [OBFUSCATION]: No hidden content, encoded strings, or deceptive Unicode characters were detected in the skill text.
Audit Metadata