audit-integrity

Name: audit-integrity
Author: github

37kstars4.6kforks

How to install audit-integrity?

github/awesome-copilot/audit-integrity

$npx -y skills add github/awesome-copilot --skill audit-integrity

Installs into the current project.

Summary

Shared audit integrity framework for all AppSec agents — enforces output quality, intellectual honesty, and continuous improvement through anti-rationalization guards, self-critique loops, retry protocols, non-negotiable behaviors, self-reflection quality gates (1-10 scoring, ≥8

Files · 1

View on GitHub

SKILL.md

1	# Audit Integrity Skill
2
3	Enforces output quality, intellectual honesty, and continuous improvement across all AppSec agents.
4
5	## When to Use
6
7	- Every security analysis, code review, threat model, or quality scan agent run
8	- Applied automatically as a post-analysis quality gate
9	- Applicable to any agent performing SAST, SCA, threat modeling, or code quality analysis
10
11	## Components
12
13	This skill provides 7 reusable capabilities. Agents apply all 7 unless their scope excludes a specific component.
14
15	\| Component \| Reference File \| Purpose \|
16	\|-----------\|---------------\|---------\|
17	\| Clarification Protocol \| [clarification-protocol.md](references/clarification-protocol.md) \| Ask ≤2 targeted questions before analysis when scope is ambiguous \|
18	\| Anti-Rationalization Guard \| [anti-rationalization-guard.md](references/anti-rationalization-guard.md) \| Table of prohibited rationalizations with mandatory responses \|
19	\| Self-Critique Loop \| [self-critique-loop.md](references/self-critique-loop.md) \| Mandatory second-pass review after initial analysis \|
20	\| Retry Protocol \| [retry-protocol.md](references/retry-protocol.md) \| Tool failure handling — retry once, then document \|
21	\| Non-Negotiable Behaviors \| [non-negotiable-behaviors.md](references/non-negotiable-behaviors.md) \| Hard rules: never fabricate, always cite evidence, report gaps \|
22	\| Self-Reflection Quality Gate \| [self-reflection-quality-gate.md](references/self-reflection-quality-gate.md) \| 1–10 scoring rubric with ≥8 threshold per category \|
23	\| Self-Learning System \| [self-learning-system.md](references/self-learning-system.md) \| Lesson/Memory templates and governance rules \|
24
25	## Execution Flow
26
27	1. Before analysis: Apply Clarification Protocol if scope is ambiguous
28	2. During analysis: Apply Anti-Rationalization Guard at every decision point
29	3. After initial pass: Execute Self-Critique Loop (mandatory second pass)
30	4. On tool failure: Apply Retry Protocol
31	5. Before delivery: Run Self-Reflection Quality Gate (all categories must score ≥8)
32	6. After delivery: Create Lessons/Memories for novel findings, false positives, or methodology gaps (see Self-Learning System)
33
34	## Agent-Specific Adaptation
35
36	Each agent customizes the Self-Critique Loop checklist and Self-Reflection Quality Gate categories to match its domain. The reference files provide the base templates; agents extend them with domain-specific items.
37
38	### Example extensions per agent type
39	- SAST/SCA agents: Add taint trace completeness and manifest coverage checks
40	- SonarQube-style agents: Add rating sanity check (A–E consistency with findings)
41	- Threat modeling agents: Add STRIDE category completeness per trust boundary
42	- Code review agents: Add trust boundary audit with data flow tracing

People who liked this also viewed

6 picks

Type

audit-integrity

37kstars4.6kforks

View on GitHub

How to install audit-integrity?

github/awesome-copilot/audit-integrity

$npx -y skills add github/awesome-copilot --skill audit-integrity

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Audit Integrity Skill
2
3	Enforces output quality, intellectual honesty, and continuous improvement across all AppSec agents.
4
5	## When to Use
6
7	- Every security analysis, code review, threat model, or quality scan agent run
8	- Applied automatically as a post-analysis quality gate
9	- Applicable to any agent performing SAST, SCA, threat modeling, or code quality analysis
10
11	## Components
12
13	This skill provides 7 reusable capabilities. Agents apply all 7 unless their scope excludes a specific component.
14
15	\| Component \| Reference File \| Purpose \|
16	\|-----------\|---------------\|---------\|
17	\| Clarification Protocol \| [clarification-protocol.md](references/clarification-protocol.md) \| Ask ≤2 targeted questions before analysis when scope is ambiguous \|
18	\| Anti-Rationalization Guard \| [anti-rationalization-guard.md](references/anti-rationalization-guard.md) \| Table of prohibited rationalizations with mandatory responses \|
19	\| Self-Critique Loop \| [self-critique-loop.md](references/self-critique-loop.md) \| Mandatory second-pass review after initial analysis \|
20	\| Retry Protocol \| [retry-protocol.md](references/retry-protocol.md) \| Tool failure handling — retry once, then document \|
21	\| Non-Negotiable Behaviors \| [non-negotiable-behaviors.md](references/non-negotiable-behaviors.md) \| Hard rules: never fabricate, always cite evidence, report gaps \|
22	\| Self-Reflection Quality Gate \| [self-reflection-quality-gate.md](references/self-reflection-quality-gate.md) \| 1–10 scoring rubric with ≥8 threshold per category \|
23	\| Self-Learning System \| [self-learning-system.md](references/self-learning-system.md) \| Lesson/Memory templates and governance rules \|
24
25	## Execution Flow
26
27	1. Before analysis: Apply Clarification Protocol if scope is ambiguous
28	2. During analysis: Apply Anti-Rationalization Guard at every decision point
29	3. After initial pass: Execute Self-Critique Loop (mandatory second pass)
30	4. On tool failure: Apply Retry Protocol
31	5. Before delivery: Run Self-Reflection Quality Gate (all categories must score ≥8)
32	6. After delivery: Create Lessons/Memories for novel findings, false positives, or methodology gaps (see Self-Learning System)
33
34	## Agent-Specific Adaptation
35
36	Each agent customizes the Self-Critique Loop checklist and Self-Reflection Quality Gate categories to match its domain. The reference files provide the base templates; agents extend them with domain-specific items.
37
38	### Example extensions per agent type
39	- SAST/SCA agents: Add taint trace completeness and manifest coverage checks
40	- SonarQube-style agents: Add rating sanity check (A–E consistency with findings)
41	- Threat modeling agents: Add STRIDE category completeness per trust boundary
42	- Code review agents: Add trust boundary audit with data flow tracing

People who liked this also viewed

6 picks

Type