nocobase-env-manage

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection.
  • Ingestion points: In SKILL.md and references/install-runbook.md, the agent is instructed to read external URLs provided by the user and follow the instructions within them if they are presented as official guides.
  • Boundary markers: There are no instructions to use boundary markers, delimiters, or to ignore malicious instructions within the fetched external content.
  • Capability inventory: The skill is granted Bash, Read, Write, Grep, and Glob tools, and can execute a wide range of nb CLI commands, including app lifecycle and CLI maintenance operations.
  • Sanitization: The instructions do not specify any sanitization, validation, or escaping of the content retrieved from external URLs before the agent processes and follows it.
  • [COMMAND_EXECUTION]: The skill is designed to execute administrative commands using the nb CLI.
  • It manages application lifecycles via nb app (start, stop, upgrade, logs).
  • It manages the CLI itself via nb self update.
  • It manages installed skills via nb skills update.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation and update of external resources.
  • It suggests installing the @nocobase/cli Node.js package from the official registry in troubleshooting scenarios.
  • It performs updates of the CLI and skills via the nb tool's native update mechanisms (nb self update and nb skills update).
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 03:59 AM
Security Audit — agent-trust-hub — nocobase-env-manage