skills/teamday-ai/agents/pomodoro/Gen Agent Trust Hub

pomodoro

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local binary (pomodoro) using the Bash tool to manage work sessions. It passes user-provided task names as command-line arguments.
  • [DATA_EXFILTRATION]: There is no evidence of network activity or data exfiltration. Session data is stored locally in a SQLite database (pomodoro.db) within the skill's configuration directory.
  • [PROMPT_INJECTION]: The skill processes user-supplied task names which are passed to the shell. While this presents an indirect injection surface, the use of quotes in the instructions mitigates immediate risk. * Ingestion points: User-provided task descriptions provided during session start. * Boundary markers: Task arguments are enclosed in double quotes in command examples. * Capability inventory: Access to the Bash and Read tools to interact with the local binary and filesystem. * Sanitization: No explicit sanitization or filtering of the task string is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 05:11 PM
Security Audit — agent-trust-hub — pomodoro