From hb-ai-toolkit
OWASP-focused security review of a file or directory. Checks for injection, auth gaps, sensitive data exposure, input validation failures, and misconfigurations. Uses Opus for thorough analysis. Run before major releases or on security-critical code.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hb-ai-toolkit:review-security [file-or-directory][file-or-directory]opusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run a security-focused review on `$ARGUMENTS`.
Run a security-focused review on $ARGUMENTS.
If $ARGUMENTS is empty, review the current working directory.
${CLAUDE_PLUGIN_ROOT}/claude/agents/security-reviewer.md in full..ts, .tsx, .js, .jsx files under the path (exclude node_modules, dist, build, .next).${CLAUDE_PLUGIN_ROOT}/claude/agents/security-reviewer.md.## Security Review: {path}
**Files scanned:** {n}
**Overall risk:** {LOW | MEDIUM | HIGH | CRITICAL}
---
{Per-file findings, only for files with issues. Files with no findings are omitted.}
---
## Summary
### Critical issues ({n})
- `{file}:{line}` — {issue}
### Warnings ({n})
- `{file}:{line}` — {issue}
### Recommendation
{One paragraph: what to fix before this code ships}
npx claudepluginhub hackberrybay/hb-ai-toolkit --plugin hb-ai-toolkitProvides CDSS development patterns for drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), and alert classification integrated into EMR workflows.