
This is a shift-left security workflow that runs SAST, SCA, and secrets detection on your PR diffs before merge. It scans only the changed code (not the entire repo), delegates heavy lifting to specialized ASPM and security reviewer agents, and returns actionable fixes as exact code diffs rather than generic advice. The whole thing is designed to stay under 2 minutes so it doesn't kill your CI pipeline. It's opinionated about blocking P0s like hardcoded secrets and SQL injection, but surfaces lower severity stuff as warnings. If you're tired of security findings showing up in prod because nobody ran Semgrep until Thursday, this automates the boring parts and actually tells you what to fix.
$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill security-test --agent claude-codeInstalls into .claude/skills of the current project.
[!IMPORTANT] Fast, continuous DevSecOps pipeline for Pull Requests and active branches. Runs SAST, SCA, and secrets detection to catch vulnerabilities before they merge.
Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.
When the user asks to perform this workflow, execute the following steps:
Goal: Execute a high-speed security audit on a branch or PR delta and stop obvious security regressions before merge.
Policy: Fast execution (< 2 mins). Focus on SAST, SCA, secrets, and trust-boundary regressions. No dynamic exploitation required.
Scope and trust gate:
git diff <base>...HEAD.<SKILLS>/common/common-security-audit/references/trust-review-policy.md.reviewContext.promptInjectionRisk to high unless host controls clearly reduce that risk.Run automated scans:
specialist-aspm-correlator.Run focused security review:
specialist-security-reviewer in fast mode for normal diffs and deep mode for auth, secrets, agent tools, or external integration changes.design-solution evidence or return BLOCKED with the missing design questions.Produce developer-ready evidence:
artifacts/security-review.md with trust class, review context, scope, source provenance, runtime contract, blockers, warnings, finding confidence, exploit path, evidence gaps, and handoff notes.artifacts/security-review.dev.md, artifacts/security-review.appsec.md, or artifacts/security-review.exec.md only when a separate audience needs it.### π‘οΈ Security Check: [PASS / FAIL]
**Scan Scope**: [branch/diff size]
**Trust Class**: [trusted|semi-trusted|untrusted]
#### π΄ Blockers
- [file:line] - [vulnerability] - [exact fix]
#### π‘ Warnings
- [risk] - [next action]
#### β
Verified
- [verified control]
Sponsors