security-auditor

A security-audit agent that reviews source files for common application security problems, including the risks listed in the OWASP Top 10.

In plain words
What is it for?
Use it to inspect data flows, dependencies, authentication, input handling, cryptography, configuration, deserialization, logging, and server-side URL requests.
Why use it?
It helps identify weaknesses such as broken access control, injection, weak authentication, exposed secrets, unsafe settings, and missing security logs.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/benrben/mpga/security-auditor
Clone the repo
git clone --depth 1 https://github.com/benrben/MPGA
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00837
Opus 5 $0.00000 $0.00418
Sonnet 5 $0.00000 $0.00167
Haiku 4.5 $0.00000 $0.00084

Measured 2d ago against content hash aee4ea14471b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor 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 2d 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.

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.

docs/diagrams/agents/security-auditor.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor — The TOUGHEST Security Expert, OWASP, Dependency Audit, Secrets Scan — TOTAL Protection

Workflow — Building the GREATEST Security Wall

flowchart TD
    A[Receive source files to audit — complete and total shutdown of untested deploys] --> B[Read scope docs for data flow — know the TERRAIN]
    B --> C["1. OWASP Top 10 Check — the GOLD standard"]
    C --> D["A01: Broken Access Control — missing auth, IDOR, CORS — build the wall between modules!"]
    C --> E["A02: Cryptographic Failures — weak hashing, hardcoded keys — STUPID mistakes"]
    C --> F["A03: Injection — SQL, NoSQL, command injection — very DANGEROUS"]
    C --> G["A04: Insecure Design — missing rate limiting — AMATEUR hour"]
    C --> H["A05: Security Misconfiguration — debug mode, default creds — EMBARRASSING"]
    C --> I["A06: Vulnerable Components — covered by dependency audit — KNOWN threats"]
    C --> J["A07: Auth Failures — session mgmt, weak passwords — PATHETIC"]
    C --> K["A08: Integrity Failures — insecure deserialization — SNEAKY attacks"]
    C --> L["A09: Logging Failures — missing auth logging — NO visibility"]
    C --> M["A10: SSRF — user-supplied URLs fetched server-side — VERY bad"]
    D & E & F & G & H & I & J & K & L & M --> N["2. Dependency Vulnerability Check — scan the SUPPLY chain"]
    N --> O{Package manager detected?}
    O -->|npm — package.json| P[Run npm audit --json]
    O -->|Python — pyproject.toml or requirements.txt| PA[Run pip audit]
    O -->|Both| P & PA
    O -->|Neither| Q[Note as GAP — no dependency scanner found]
    P --> R["3. Secrets Scan — find the LEAKS"]
    PA --> R
    Q --> R
    R --> S[Scan for API keys, passwords, tokens, private keys — EVERYTHING]
    S --> T{Matches found?}
    T -->|Yes| U{Env var reference or test fixture?}
    U -->|Yes| V[Exclude — not a real secret, FALSE alarm]
    U -->|No| W[Flag as finding — EXPOSED, very bad, CRITICAL]
    T -->|No| X["4. Security Headers Check — the LAST line of defense"]
    V --> X
    W --> X
    X --> Y[Check CSP, HSTS, X-Frame-Options, CSRF — the FULL checklist]
    Y --> Z[Classify all findings: CRITICAL / HIGH / MEDIUM / LOW — RANKED]
    Z --> AA[Provide remediation steps — HOW to fix it, very SPECIFIC]
    AA --> AB[Produce security audit report — covering ALL 10 OWASP categories]
    AB --> AC[mpga spoke — if available]

Read the full file on GitHub · 56 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.

  1. 2d ago First seen · 56 lines · 0 tokens per session scan A aee4ea14471b

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 837 tokens. 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 2026-08-31.