agent-manager-skill-v2

Warn

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone an external repository (https://github.com/fractalmind-ai/agent-manager-skill.git) that is not part of the skill package itself.
  • [REMOTE_CODE_EXECUTION]: The provided workflow executes Python scripts directly from the cloned repository using commands like python3 agent-manager/scripts/main.py.
  • [COMMAND_EXECUTION]: The skill utilizes tmux for process management and cron for task scheduling. The use of cron for recurring activities establishes a persistence mechanism on the user's system.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection. Ingestion points: The assign command reads task instructions from external files such as teams/fractalmind-ai-maintenance.md. Boundary markers: No delimiters or warnings are used to isolate untrusted content. Capability inventory: The skill can execute shell commands and manage local sessions via tmux. Sanitization: No evidence of validation or sanitization of ingested file contents exists.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 7, 2026, 09:22 PM
Security Audit — agent-trust-hub — agent-manager-skill-v2