Audit Integrity Gate

Use after security analysis, code review, threat modeling, or quality scans to catch fabricated evidence, rationalized gaps, incomplete second passes, and unreported tool failures.

9 stars 3 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add sandbaseai/workbuddy-skill --skill audit-integrity-gate
Manual install
git clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/audit-integrity-gate ~/.claude/skills/audit-integrity-gate

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Audit Integrity Gate

## Scope

Apply this gate to every security review, SAST/SCA result, threat model, code review, reliability scan, or other analysis where an Agent could overstate confidence. It governs the integrity of the analysis and report; it does not replace domain-specific tests, scanners, or human approval required by policy.

## Integrity contract

Before analysis, record the target revision, scope, exclusions, tools and versions, access limitations, and the exact questions being answered. Every finding must map to observable evidence: a path and line, reproducible command, trace, configuration, test, source citation, or explicitly marked inference. Treat unknown as unknown; never fill a gap with plausible text.

At each decision point ask:

- What fact supports this conclusion?
- What would falsify it?
- Did I inspect the relevant consumer, trust boundary, history, configuration, or platform path?
- Am I downgrading a risk because it is inconvenient, difficult to reproduce, or outside my preferred tool?
- Is the proposed remediation required by an observed problem, or is it speculative scope?

Record contradictions and coverage gaps instead of silently resolving them in favor of a clean report.

## Mandatory second pass

After the initial analysis, perform a fresh review with the first-pass conclusion temporarily treated as untrusted. Check:

1. scope and revision coverage;
2. evidence links and line/command accuracy;
Read the full skill on GitHub

Details

Skill name
audit-integrity-gate
Path
skills/audit-integrity-gate/SKILL.md
License
MIT
Repo updated
8 September 2026

FAQ

What does the Audit Integrity Gate skill do?

Use after security analysis, code review, threat modeling, or quality scans to catch fabricated evidence, rationalized gaps, incomplete second passes, and unreported tool failures.

How do I install the Audit Integrity Gate skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill audit-integrity-gate. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Audit Integrity Gate popular?

It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.

Related skills

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.