kay-tee-khaw
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill package is composed of informational Markdown files and structured JSON data representing academic sources. No security risks were identified during the analysis of any file.
- [NO_CODE]: There are no executable scripts (e.g., .py, .js, .sh) or binaries included in the skill. The logic is entirely contained within natural language instructions and persona definitions.
- [PROMPT_INJECTION]: The instructions in
SKILL.mdandAGENTS.mdare well-structured and focused on academic reasoning. They do not contain any patterns attempting to bypass safety protocols or override system instructions. - [DATA_EXFILTRATION]: No network operations or sensitive file system access patterns were detected. All external URLs listed in the sources and discovery files are legitimate links to journals (Nature, PLOS Medicine, Oxford Academic), institutional websites (University of Cambridge), or news organizations.
- [COMMAND_EXECUTION]: There are no shell commands or dynamic context injection patterns (
!command) present in the skill's instructions.
Audit Metadata