Skills
skills/catlog22/claude-code-workflow/team-coordinate/Gen Agent Trust Hub

team-coordinate

Warn

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a significant surface for indirect prompt injection.\n
  • Ingestion points: User-provided task descriptions are ingested in SKILL.md and processed by the coordinator in roles/coordinator/role.md.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the dynamic role-spec generation logic in roles/coordinator/role.md or specs/role-spec-template.md.\n
  • Capability inventory: The system can spawn sub-agents via the Agent tool and execute system-level commands using Bash as defined in SKILL.md.\n
  • Sanitization: There is no evidence of escaping, validation, or filtering of user input before it is interpolated into instructions for spawned worker agents.\n- [COMMAND_EXECUTION]: The skill grants broad system access via the Bash tool to dynamically generated worker roles.\n
  • Evidence: SKILL.md allows the Bash tool for all workers. The coordinator spawns team-worker agents with these capabilities to perform tasks like code implementation or research, which involves executing arbitrary shell commands based on runtime-generated instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 06:57 AM