calendar-management
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Detailed inspection of the skill files revealed no malicious patterns, obfuscation, or security bypasses. The logic is consistent with the stated purpose of calendar management.\n- [COMMAND_EXECUTION]: The skill utilizes the 'bash' tool to execute its core logic via a Python script. This is the expected and documented method for the agent to interface with the local environment.\n- [PROMPT_INJECTION]: The skill's instructions in SKILL.md provide operational guidance to the AI, such as automating date calculations. These are functional improvements for user experience rather than attempts to override system safety protocols.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it retrieves event data from an external API (Lark). This is a standard risk for tools that process external content, and the implementation follows best practices for data handling.
Audit Metadata