nocobase-notification-manage

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to interact with the NocoBase environment through the nb CLI. It executes resource management commands such as api resource list, create, update, and get to manage notificationChannels and notificationSendLogs. All commands are directed at NocoBase-specific resources and follow a structured format.
  • [PROMPT_INJECTION]: The skill ingests data from external logs and channel metadata, which constitutes a potential surface for indirect prompt injection. However, the risk is mitigated by the diagnostic-only use case and the focus on structured API operations.
  • Ingestion points: The skill reads notificationSendLogs (reason, message) and notificationChannels (title, description) from the NocoBase environment into the agent context.
  • Boundary markers: No explicit markers are used to delimit untrusted log content from instructions.
  • Capability inventory: The skill possesses the Bash tool to execute environment-specific CLI commands.
  • Sanitization: No explicit sanitization or filtering logic is provided for external content before interpolation.
  • [CREDENTIALS_UNSAFE]: While the skill manages sensitive SMTP credentials, it specifically prohibits the exposure of passwords and tokens. It mandates redacting the password field in all readback reports and requires secondary confirmation for credential updates, demonstrating a safe approach to secret handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:37 AM
Security Audit — agent-trust-hub — nocobase-notification-manage