A one-command security audit pipeline for a codebase, including large projects. It creates an architecture summary, models threats, checks high-risk modules, and writes a security report.

Use it to review a project's security, identify risky parts, and produce a list of actionable findings. Run it against a specified code folder.

It removes the need to plan and coordinate a broad security review by hand. It also keeps the audit plan and review history as files in the project.

full-audit — Command for Claude Code by allsmog

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add allsmog/vuln-scout

Claude Code

/plugin install vuln-scout

Made for: Claude Code.

Or install vuln-scout, the plugin that ships this one along with the rest of its 32 skills, 15 commands, 9 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/allsmog/vuln-scout/full-audit/github.svg)](https://agentmods.dev/commands/allsmog/vuln-scout/full-audit)

Your own site

<a href="https://agentmods.dev/commands/allsmog/vuln-scout/full-audit"><img src="https://agentmods.dev/badge/commands/allsmog/vuln-scout/full-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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/allsmog/vuln-scout/full-audit"><img src="https://agentmods.dev/badge/commands/allsmog/vuln-scout/full-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 19,717 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 4 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.19717
Opus 5	$0.00015	$0.09858
Sonnet 5	$0.00006	$0.03943
Haiku 4.5	$0.00003	$0.01972

Measured 9d ago against content hash f555d5cc7faa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

full-audit scanned grade C with 4 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 9d ago.

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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -L "https://github.com/joernio/joern/releases/latest/download/joern-install.sh" | bash

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

if grep -q "CRITICAL.*VERIFIED" .claude/audit-report.md; then

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -L "https://github.com/joernio/joern/releases/latest/download/joern-install.sh" | bash

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- TypeScript sinks: eval, child_process, DOM APIs

vuln-scout/commands/full-audit.md · 1,955 lines

How it starts

The opening of the file, as written. The whole thing — 1,955 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comprehensive Security Audit

One command to audit any codebase, regardless of size.

/vuln-scout:full-audit /path/to/code

Shared Prompt Fragments

Before executing this command, read these canonical fragments and treat them as the source of truth for phase order, artifacts, and safety defaults:

vuln-scout/references/full-audit/phases.md
vuln-scout/references/full-audit/artifact-contract.md
vuln-scout/references/full-audit/safety.md

The detailed body below is compatibility guidance for Claude Code command execution. If it conflicts with a shared fragment, follow the shared fragment.

This command automatically:

Detects if codebase is too large for direct analysis
Creates compressed architecture scope (language-aware)
Generates system-level threat model
Writes a persisted audit plan to .claude/audit-plan.md
Records adversarial review rounds in .claude/review-ledger.json
Identifies and audits high-risk modules
Produces actionable security report

What This Command Does

┌─────────────────────────────────────────────────────────────┐
│                    FULL AUDIT PIPELINE                       │
├─────────────────────────────────────────────────────────────┤
│                                                              │
│  Step 0: SIZE CHECK & ARCHITECTURE DISCOVERY                 │
│  └─> Measure tokens, parse docker-compose/supervisord       │
│  └─> Map services, ports, internal connectivity              │
│      < 150k tokens  → Direct audit                          │
│      > 150k tokens  → Architecture-first workflow           │
│                                                              │
│  Step 1: ARCHITECTURE SCOPE (if large)                       │
│  └─> Language-aware compression (Go: 97%, JS/TS: 80%)       │
│                                                              │
│  Step 1.5: FRAMEWORK PATTERN SCAN                            │
│  └─> Next.js Server Actions, Flask SSTI patterns            │
│  └─> Framework-specific security anti-patterns              │
│                                                              │
│  Step 2: THREAT MODEL                                        │
│  └─> STRIDE analysis, DFDs, trust boundaries                │
│                                                              │
│  Step 2.5: AUDIT PLAN + REVIEW                               │
│  └─> Persist strategy, attack surfaces, verification plan    │
│  └─> 3 review angles: coverage, prioritization, mismatch     │
│                                                              │
│  Step 3: MODULE IDENTIFICATION                               │
│  └─> Rank modules by risk, select top N                     │
│                                                              │
│  Step 4: DEEP DIVE AUDIT (per module)                        │
│  └─> Sink search, data flow tracing, finding review loops    │
│  └─> Semgrep + Joern + CodeQL + extended detectors          │
│  └─> Semantic FP checks, cross-tool correlation             │
│  └─> Auto-propagation of verified patterns                  │
│                                                              │
│  Step 4.5: CLAUDE SEMANTIC ANALYSIS                          │
│  └─> AI-native reasoning on unresolved findings             │
│  └─> Exploitability assessment, sanitizer bypass analysis   │
│                                                              │
│  Step 5: CHAIN + TRIAGE                                      │
│  └─> Automated attack chain detection (5 patterns)          │
│  └─> Auto-triage (auth, exposure, test files)               │
│  └─> Business context CVSS adjustment                       │
│                                                              │
│  Step 6: REPORT + ARTIFACTS                                  │
│  └─> Findings with remediation + knowledge graph            │
│  └─> PoC generation for verified findings (optional)        │
│                                                              │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 1,955 lines

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.

9d ago First seen · 1,955 lines · 29 tokens per session scan C f555d5cc7faa

Subscribe to this mod's changes

full-audit is a command published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 19,717 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 4 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Debugging Security appsec claude-code-plugin sast semgrep threat-modeling

full-audit

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Downloads and executes remote codemediumSupply chain

Reads agent configuration directorieslowAgent snooping

Makes network callslowCapability

Runs shell commandslowCapability

How it starts

Comprehensive Security Audit

Shared Prompt Fragments

What This Command Does

What this file has done since we first saw it

Other commands, from other repositories

linkerd

debug

ia-report-bug

data-flow-analysis

duck-off

bug