team-assign

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Orchestrates team management tasks by invoking a local script, team-manager.py, with arguments derived from user input. This facilitates actions like capacity checking and task assignment.
  • [PROMPT_INJECTION]: The skill incorporates user-provided task descriptions and external brand profiles into its operational logic, creating a surface for potential indirect prompt injection. * Ingestion points: User-supplied task descriptions and notes; brand configuration files (profile.json, guidelines/_manifest.json). * Boundary markers: None explicitly specified in the skill instructions. * Capability inventory: Execution of local Python scripts, filesystem access for brand data and logs, and external messaging via Slack/Email MCP. * Sanitization: No explicit sanitization or validation of input strings before processing or passing to the management script.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 01:03 PM