gen-notifier
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill involves the execution of the
terminal-notifiercommand-line tool via the shell to display task updates. - [INDIRECT_PROMPT_INJECTION]: The skill uses dynamic task-related strings to populate notification titles and messages, which represents a potential surface for indirect prompt injection.
- Ingestion points: Task summaries and status indicators from the agent's current context are interpolated into CLI command arguments.
- Boundary markers: The skill mandates strict regex validation for the
{THREAD_ID}parameter to ensure only canonical UUIDs are processed. - Capability inventory: The agent utilizes shell command execution to interact with the macOS notification system.
- Sanitization: The instructions explicitly warn against using the
-executeflag and other dangerous parameters, which mitigates the risk of command injection from malicious task content.
Audit Metadata