Audit Integrity Agent Skill
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 threshold), and a self-learning system with lesson/memory governance for security analysis agents.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/github/awesome-copilot --skill audit-integrityWhat comes with it
14 404 bytes besides the instructionThe instruction itself
6 sections, as written by the authorAudit Integrity Skill
Enforces output quality, intellectual honesty, and continuous improvement across all AppSec agents.
When to Use
- Every security analysis, code review, threat model, or quality scan agent run
- Applied automatically as a post-analysis quality gate
- Applicable to any agent performing SAST, SCA, threat modeling, or code quality analysis
Components
This skill provides 7 reusable capabilities. Agents apply all 7 unless their scope excludes a specific component.
| Component | Reference File | Purpose |
|-----------|---------------|---------|
| Clarification Protocol | clarification-protocol.md | Ask ≤2 targeted questions before analysis when scope is ambiguous |
| Anti-Rationalization Guard | anti-rationalization-guard.md | Table of prohibited rationalizations with mandatory responses |
| Self-Critique Loop | self-critique-loop.md | Mandatory second-pass review after initial analysis |
| Retry Protocol | retry-protocol.md | Tool failure handling — retry once, then document |
| Non-Negotiable Behaviors | non-negotiable-behaviors.md | Hard rules: never fabricate, always cite evidence, report gaps |
| Self-Reflection Quality Gate | self-reflection-quality-gate.md | 1–10 scoring rubric with ≥8 threshold per category |
| Self-Learning System | self-learning-system.md | Lesson/Memory templates and governance rules |
Execution Flow
- Before analysis: Apply Clarification Protocol if scope is ambiguous
- During analysis: Apply Anti-Rationalization Guard at every decision point
- After initial pass: Execute Self-Critique Loop (mandatory second pass)
- On tool failure: Apply Retry Protocol
- Before delivery: Run Self-Reflection Quality Gate (all categories must score ≥8)
- After delivery: Create Lessons/Memories for novel findings, false positives, or methodology gaps (see Self-Learning System)
Agent-Specific Adaptation
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.
Example extensions per agent type
- SAST/SCA agents: Add taint trace completeness and manifest coverage checks
- SonarQube-style agents: Add rating sanity check (A–E consistency with findings)
- Threat modeling agents: Add STRIDE category completeness per trust boundary
- Code review agents: Add trust boundary audit with data flow tracing
Other skills for the same job
different authors, same section of the catalogue
> FHIR REST endpoints (Patient, Observation, Encounter, Condition, MedicationRequest), (2) Validating FHIR resources and returning proper HTTP status codes and error responses, (3) Implementing SMART on FHIR authorization and OAuth scopes, (4) Working with Bundles, transactions, batch operations, or search pagination. Covers FHIR R4 resource structures, required fields, value sets (status codes, gender, intent), coding systems (LOINC, SNOMED, RxNorm, ICD-10), and OperationOutcome error handling.
Interact with ClawDirect, a directory of social web experiences for AI agents. Use this skill to browse the directory, like entries, or add new sites. Requires ATXP authentication for MCP tool calls. Triggers: browsing agent-oriented websites, discovering social platforms for agents, liking/voting on directory entries, or submitting new agent-facing sites to ClawDirect.
Opt out of the OneCLI gateway and supply Anthropic credentials from .env instead. For users who want simple .env-based credential management without the OneCLI agent vault. Reads the API key or OAuth token from .env and injects it into the container's API requests.
Cross-product Zoom reference skill. Use after the workflow is clear when you need shared platform guidance, app-model comparisons, authentication context, scopes, marketplace considerations, or API-vs-MCP routing.
>- Static source-code vulnerability scan. Reads a target directory (and THREAT_MODEL.md if present), spawns parallel review subagents per focus area, and writes VULN-FINDINGS.json + .md for /triage to consume. Read-only — no building, running, or network. For execution-verified crashes, use vuln-pipeline instead. Use when asked to "scan for vulns", "review this code for security issues", "find bugs in <dir>", or as the step between /threat-model and /triage.
Hunt Session Management vulnerabilities — session fixation (no regeneration on login), insufficient invalidation on logout / password-change / email-change, predictable or low-entropy session IDs, JWT-as-session with no exp/revocation, refresh-token rotation/reuse-detection gaps, OAuth/SSO session linkage, device-bound-session (DBSC) downgrade, and cookie attribute issues (Secure/HttpOnly/SameSite/__Host-). Validate with TWO real sessions (attacker A + victim B), body-diff every 200, and OOB confirmation for theft chains. Medium to Critical (fixation→admin hijack, no-invalidation→persistent ATO).
> Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring `doca_aes_gcm_task_encrypt` / `_task_decrypt`, querying `doca_aes_gcm_cap_*` for per-key-type (only `DOCA_AES_GCM_KEY_128` / `_256` — AES-192 not supported) and per-task support, sizing plaintext against the max-buf cap, setting source / destination mmap permissions, validating with a NIST GCMVS or RFC 5288 vector, or debugging DOCA_ERROR_* including the security-critical tag-verification-failed outcome on decrypt. Trigger even when the user does not explicitly mention "DOCA AES-GCM" or IO_FAILED", "auth tag isn't verifying", "NOT_PERMITTED on my encrypt buffer", "is AES-192-GCM on this BlueField" (no), or "encrypted record came back tampered". Refuse and route elsewhere for non-GCM AES modes (CBC / CTR / XTS — CPU OpenSSL), key management (KMS / HSM / rotation), SHA (doca-sha), or general AEAD background.
>- Run a full 6-dimension health check of this Claude Code skills marketplace repo — code/script safety, documentation/SSOT consistency, security/PII leaks, open-PR triage, open-issue triage, and marketplace-manifest integrity — via a parallel fan-out Dynamic Workflow, then verify the serious findings and report them by priority. Use this whenever the user asks to check the repo, run a health check, do a full sweep/audit before a release, 全面体检, 检查仓库状态, 看看仓库健康吗, 审计一下仓库, or asks whether the PRs / issues / docs / versions / PII are in good shape across the board — even if they never say the word "workflow". Reach for it for any broad "is this whole repo OK" request, not just one-file checks.
How to use it
Take github/audit-integrity from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.