The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on a local Python script team-manager.py to perform core operations including roster management, capacity checks, and task assignment. It passes user-supplied inputs such as task descriptions, channel names, and notes as arguments to this script.
[DATA_EXFILTRATION]: The skill reads sensitive brand profiles, SOPs, and configuration files from the user's home directory (~/.claude-marketing/). It is designed to include relevant brand context in notifications sent via external Slack or Email MCP integrations, which is a functional requirement for the task assignment process.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via user-provided task descriptions and notes.
Ingestion points: Task description and Notes fields in SKILL.md.
Boundary markers: None identified in the prompt instructions.
Capability inventory: Executes subprocesses (team-manager.py), writes to local logs (assignments.json), and performs network operations via Slack/Email MCP.
Sanitization: No specific sanitization or escaping of user input is documented before passing it to the agent or the helper script.

team-assign