knowledge
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or security risks were identified in this skill. It follows a legitimate workflow for internal knowledge management.
- [DATA_EXFILTRATION]: The skill exclusively uses local Obsidian tools to read and write markdown files. It does not contain network operations, hardcoded credentials, or access to sensitive system paths.
- [COMMAND_EXECUTION]: No usage of shell commands, subprocesses, or dynamic code execution was found. All operations are confined to the agent's defined environment.
- [PROMPT_INJECTION]: The skill contains no instructions to bypass safety filters, extract system prompts, or override the agent's core instructions.
Audit Metadata