Security audit
Security checks for vulnerabilities and agentic risk
This skill is a code-review workflow helper that asks an agent to inspect git diffs and report issues; I found no hidden install, persistence, credential, network, or destructive behavior.
Install this if you want an agent to request structured code reviews of repository changes. Expect it to read git diffs and possibly use a reviewer subagent, but the inspected artifacts do not show hidden execution, data exfiltration, persistence, or credential use.
The description says to use the skill when 'completing tasks, implementing major features, or before merging,' which are broad, common workflow states rather than specific trigger phrases or constrained activation conditions. Without clearer boundaries or exclusion conditions, the skill could be invoked more often than intended across routine development work.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Give clear verdict
**DON'T:**
- Say "looks good" without checking
- Mark nitpicks as Critical
- Give feedback on code you didn't review
- Be vague ("improve error handling")
No suspicious patterns detected.