agent-team

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior detected. The skill's operations are consistent with its described functionality as an agent team orchestrator.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute routine development tasks such as Git branching, committing, merging, and running project-specific builds or security scans.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) because it ingests user-defined task descriptions to decompose them into instructions for sub-agents.
  • Ingestion points: User-provided task descriptions via the skill's main argument (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the orchestration logic.
  • Capability inventory: The skill has access to shell execution (Bash), file modification (Write, Edit), and the ability to spawn and instruct other agents (TeamCreate).
  • Sanitization: No validation or sanitization of the input task description is performed before it is used to generate prompts for sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 07:08 AM
Security Audit — agent-trust-hub — agent-team