team-stop
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands including
ls,mkdir, andrm -rf. These are used to manage the team state within the~/.claude/teams/directory and create backups in.team-profiles/. These operations are consistent with the skill's primary function of resource management. - [PROMPT_INJECTION]: The skill is subject to potential indirect prompt injection as it ingests and displays data from external configuration files and task management tools.
- Ingestion points: Team configuration files (
config.json) and tool outputs fromTaskListandTaskGet(file: SKILL.md). - Boundary markers: Absent; the skill reads and reflects content like task subjects and team descriptions directly into the agent's context.
- Capability inventory: File system deletion (
rm -rf), file writing (Write), and inter-agent communication (SendMessage) (file: SKILL.md). - Sanitization: None; the skill processes the retrieved data as trusted input for its display and cleanup logic.
Audit Metadata