The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external CalDAV servers and imported ICS files. Ingestion points were found in scripts/events.py, scripts/todos.py, and scripts/calendars.py, where fields such as event summaries, descriptions, and locations are read. The skill does not implement boundary markers or sanitization for these strings, which could allow a malicious calendar entry to influence the agent's behavior. \n- [COMMAND_EXECUTION]: The scripts/radicale.py script uses the subprocess module to execute system commands including systemctl status, pgrep, and htpasswd. While these calls are implemented using argument lists (avoiding shell injection), they provide the agent with the capability to monitor and manage local system services and user credentials.

caldav