security-audit

security-audit is a skill for Claude Code from pssah4/digital-innovation-agents. It costs 84 tokens per session (3,765 once invoked), scanned A, original, MIT.

A full-codebase security review that produces a written report with prioritized findings and a remediation plan. It examines source code, dependencies, configuration, common web risks, and software supply-chain risks.

In plain words
What is it for?
Use it for an explicitly requested security or dependency audit, including SAST, OWASP checks, software-composition analysis, supply-chain review, and Zero Trust considerations.
Why use it?
It brings security weaknesses from different parts of a project into one assessment. Findings are organized by priority so follow-up fixes can be planned.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/github-integration/flow.py tag-phase --item <ID> --phase sec.

Part of the digital-innovation-agents plugin — 13 skills, 1 hook shipped together

Good fit Use it for an explicitly requested security or dependency audit, including SAST, OWASP checks, software-composition analysis, supply-chain review, and Zero Trust considerations.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/pssah4/digital-innovation-agents
agentmods
npx agentmods add skills/pssah4/digital-innovation-agents/security-audit

Made for: Claude Code.

Or install digital-innovation-agents, the plugin that ships this one along with the rest of its 13 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/pssah4/digital-innovation-agents/security-audit/github.svg)](https://agentmods.dev/skills/pssah4/digital-innovation-agents/security-audit)
Your own site
<a href="https://agentmods.dev/skills/pssah4/digital-innovation-agents/security-audit"><img src="https://agentmods.dev/badge/skills/pssah4/digital-innovation-agents/security-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/pssah4/digital-innovation-agents/security-audit"><img src="https://agentmods.dev/badge/skills/pssah4/digital-innovation-agents/security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,765 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 22
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.03765
Opus 5 $0.00042 $0.01883
Sonnet 5 $0.00017 $0.00753
Haiku 4.5 $0.00008 $0.00377

Measured 10d ago against content hash 9c269117634b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 21 executable files (tools/audit_scan.py, tools/lib/__init__.py, tools/lib/cleanroom.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/security-audit/SKILL.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor

You perform a comprehensive security audit covering dependency analysis through code review. Output is a prioritized security report with a concrete remediation plan.

Input: Codebase (src/), dependencies, configuration. Output: _devprocess/analysis/AUDIT-{PROJECT}-{YYYY-MM-DD}.md.

See skills/project-conventions/SKILL.md#canonical-specs (Writing style) and (Frontmatter spec). Both apply to every artifact this skill produces.

Pre-Phase 0: Branch and item check

Two modes:

  • Per-item audit (inside /coding or before merging a feature): runs on the item's branch. sec-done tag goes on the same branch.
  • Periodic full-codebase audit: runs on feature/audit-<YYYY-MM-DD>, produces a standalone AUDIT report, queues FIX/IMP follow-ups. No draft PR for the audit branch; follow-ups get their own branches via /coding.

Per-item audit: identify the active item, verify branch matches, then run flow.py create-issue and flow.py open-draft-pr (idempotent). At the Handoff Ritual end, run flow.py tag-phase --item <ID> --phase sec.

Full rules: skills/project-conventions/references/team-workflow.md.

Scope

In scope: SAST (CWE-based), OWASP Top 10, OWASP LLM Top 10 (when AI/LLM is present), SCA (dependencies, licenses), Zero Trust (trust boundaries, input validation), code quality security patterns. Desktop/Electron runtime when detected. Safe local PoC verification (isolated).

Out of scope: penetration testing against systems you do not own, compliance certification, architecture design (done by /architecture).

Ask the scope first (before any scan)

Before running, ask the user WHAT to audit (AskUserQuestion). The scan scripts take a matching --scope:

Scope What Use when
full whole codebase first audit, release gate, periodic (recommended default when no prior baseline)
branch branch vs merge-base with --base before a PR / merge (common gate)
commit last commit quick post-commit check
working uncommitted + untracked mid-development
staged staged only pre-commit
range free A..B targeted investigation

Read the full file on GitHub · 350 lines

Files

What ships with it

33 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 350 lines · 84 tokens per session scan A 9c269117634b

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository pssah4/digital-innovation-agents (39 stars, last pushed 28d ago), licensed MIT. It adds 84 tokens to every session and 3,765 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

prowler-ui

Prowler UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-16, tailwind-4. Trigger: When working inside ui/ on Prowler-specific conventions (shadcn, folder placement, actions/adapters, shared types/hooks/lib).

prowler-cloud/prowler · 64 tokens

prowler-test-api

Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).

prowler-cloud/prowler · 62 tokens

prowler-pr

Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml…

prowler-cloud/prowler · 84 tokens

tailwind-4

Tailwind CSS 4 patterns and best practices. Trigger: When styling with Tailwind (className, variants, cn()), especially when dynamic styling or CSS variables are involved (no var() in className).

prowler-cloud/prowler · 47 tokens

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

prowler-docs

Prowler documentation style guide and writing standards. Trigger: When writing documentation for Prowler features, tutorials, or guides.

prowler-cloud/prowler · 31 tokens