Security audit
Security checks for vulnerabilities and agentic risk
This skill claims to manage git worktrees but its instructions are broad, vague, and ask for command execution plus generic API and data-processing workflows.
Review this carefully before installing. It is not clearly malicious, but it is under-scoped for a command-capable skill: use it only if you intend to inspect and approve each command, and do not provide API keys or credentials unless the publisher narrows and explains why they are needed.
The skill is presented as a git-worktree utility, but most of the document describes generic API, data processing, credentials, and automation behavior. This mismatch can cause an agent or user to grant broader trust, permissions, or invocation scope than intended, increasing the chance of unsafe execution with the powerful exec tool.
The core-function section contradicts the stated purpose by advertising broad data-processing and workflow orchestration capabilities rather than isolated git workspace management. In a skill that has exec access, this kind of scope confusion is dangerous because it normalizes actions outside the expected trust boundary and makes misuse harder to detect.
The request/response schema and onboarding steps describe a generic content-processing API rather than a local git-worktree helper. That mismatch can mislead orchestrators into passing arbitrary content or credentials to a skill that also exposes command execution, creating opportunities for unsafe automation and accidental overreach.
Documenting external API keys, network failures, and remote-service behavior is inconsistent with a local git-worktree skill and suggests undeclared external dependencies. While less severe than direct command injection, this can still mislead users into provisioning secrets or enabling networked behavior that the skill should not require.
The trigger condition 'when the user needs to perform related operations' is so broad that the skill may activate in contexts far beyond git worktree setup. Over-broad activation is risky for a skill with exec access because it can be selected for unrelated tasks and execute commands under an inappropriately broad interpretation of user intent.
The description uses expansive language covering development automation, data analysis, and process orchestration without clear limits, even though the skill name suggests a narrowly scoped git utility. This broad framing increases the likelihood of over-selection, excessive permissions, and user confusion about what the skill is allowed to do.
No suspicious patterns detected.
