Security audit
Security checks for vulnerabilities and agentic risk
This brainstorming skill is mostly coherent, but it can trigger very broadly and instructs the agent to create and commit design documents without a clearly separate approval step.
Review this skill before installing if you do not want planning conversations to create files or commits automatically. It appears suitable as a design-planning helper only if you are comfortable requiring explicit user confirmation before any docs/plans write or git commit.
The instruction that the skill 'MUST' be used before any creative work is overly broad and can force invocation across a large set of normal development activities. Because the skill also includes write and commit behaviors, broad triggering increases the chance of unnecessary questioning, workflow interception, and unintended repository modification.
The skill is positioned as a brainstorming and design aid, but it also instructs the agent to write a file and commit changes to git. That expands the skill from advisory behavior into repository mutation, which violates least privilege and can cause unintended persistent changes during what should be a low-risk planning workflow.
Committing to git is a privileged side effect that is not clearly necessary for idea exploration or design discussion. If invoked broadly, this could create unwanted commits, pollute history, or be abused to persist content the user did not intend to save.
No suspicious patterns detected.
