skills/5dive-ai/skills/5dive-cli/Gen Agent Trust Hub

5dive-cli

Warn

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONREMOTE_CODE_EXECUTIONCREDENTIALS_UNSAFEPERSISTENCEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The 5dive CLI enables extensive control over the host environment, allowing agents to manage Linux users, systemd services, and tmux sessions through a sudo wrapper.
  • [PRIVILEGE_ESCALATION]: The skill includes a command, 5dive agent grant <name> root, specifically designed to confer full root privileges to agents. It also provides the 5dive host toolset for system-level remediation.
  • [REMOTE_CODE_EXECUTION]: Agents can install and execute remote code via 5dive crew install <git-url>, 5dive plugin add, and 5dive agent import, which fetches persona packs and plugins from external sources.
  • [CREDENTIALS_UNSAFE]: The skill manages sensitive credentials using a vault and environment files (/etc/5dive/connectors/). It provides mechanisms for agents to request secrets from humans via one-time secure links and to store them for tool usage.
  • [PERSISTENCE]: The skill facilitates long-term persistence through heartbeat cron jobs that wake agents, recurring task templates, and the ability to schedule actions using cron syntax via 5dive council schedule.
  • [DYNAMIC_EXECUTION]: The messaging system (agent send) is susceptible to command substitution if messages are improperly quoted. Additionally, commands like task verify, objective --metric-cmd, and council schedule --context-cmd involve executing dynamic shell snippets at runtime.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from untrusted sources, including external chat channels (Telegram, Discord) and shared task descriptions, creating a surface for indirect prompt injection.
  • Ingestion points: Inter-agent messages, human chat inputs, shared task bodies, and external event triggers.
  • Boundary markers: The skill suggests using single quotes for messages and provides a --message-file flag to mitigate shell injection risks.
  • Capability inventory: Access to system-level commands, Git operations, and network communication via bots.
  • Sanitization: Relies primarily on instructional warnings to the agent rather than strict programmatic enforcement or escaping of all inputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 16, 2026, 11:13 PM