skills/ellmos-ai/skills/kalender/Gen Agent Trust Hub

kalender

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Extensive analysis of the skill's instructions and its Python implementation shows no signs of malicious intent, obfuscation, or unauthorized access to sensitive system resources.\n- [COMMAND_EXECUTION]: The kalender_core.py script provides a CLI for managing appointments. The source code uses the standard sqlite3 library with parameterized inputs for all database operations, ensuring that user-provided titles or descriptions cannot trigger SQL injection.\n- [DATA_EXFILTRATION]: The core tool is designed to be offline. It lacks any network-facing code and strictly manages data within a local store.db file or user-specified local export paths. No unauthorized data transmission patterns were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes event metadata provided by the user. These inputs are correctly sanitized and escaped before being stored in the database or exported to the ICS format, preventing them from being misinterpreted as commands by the agent or other tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 05:44 AM