← using-git-worktrees (superpowers)
using-git-worktrees (superpowers) — agentic threat model
This agent skill possesses high risk due to its ability to execute real git commands directly on the host system, creating a significant attack surface for host compromise or code manipulation if prompt injection or tool misuse occurs.
OWASP AIVSS score rationale
| Autonomy of Action | 0.60 | |
| Goal-Driven Planning | 0.40 | |
| Self-Modification | 0.10 | |
| Dynamic Tool Use | 0.70 | |
| Persistent Memory | 0.20 | |
| Contextual Awareness | 0.40 | |
| Dynamic Identity | 0.30 | |
| Multi-Agent Interactions | 0.20 | |
| Non-Determinism | 0.30 | |
| Opacity & Reflexivity | 0.30 |
Scored with the canonical OWASP AIVSS formula (AIVSS calculator reference); agentic risk factors estimated from the agent’s described capabilities.
MAESTRO 7-layer threat model
Per-layer threats for this agent. Layers tagged “not certain from listing” are general, caveated commentary where the public description didn’t pin that layer.
Not certain from the listing — The listing does not specify the underlying LLM/model used to drive this skill. Standard threats like adversarial prompt injection could lead to arbitrary git command execution.
Not certain from the listing — No mention of vector databases, RAG, or training data pipelines. The agent operates directly on local git repositories.
The agent framework orchestrates git commands. The primary threat is tool misuse or insecure tool integration, where malicious inputs could manipulate git worktree arguments to execute arbitrary shell commands or access unauthorized directories.
The agent runs real git commands on the host. This presents a high risk of host compromise, privilege escalation, or directory traversal if the execution environment is not strictly sandboxed.
Not certain from the listing — There is no mention of logging, guardrails, or evaluation frameworks to monitor the execution of git commands.
Not certain from the listing — No details are provided regarding authentication, authorization, or audit policies governing who can invoke this skill or what repositories it can access.
This is a 'superpowers skill' designed to be integrated into an agent ecosystem. If a compromised agent invokes this skill, it could abuse the host's git environment to exfiltrate code or inject malicious commits.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).