dnp-security-auditor

dnp-security-auditor is an agent for Claude Code from zdanovichnick/dotnet-pilot. It costs 36 tokens per session (1,141 once invoked), scanned A, original, MIT.

A read-only security auditing agent for .NET APIs. It checks for issues such as injection, exposed secrets, weak authentication or authorization, unsafe input handling, and vulnerable dependencies.

In plain words
What is it for?
Use it to review controllers and API endpoints against common web risks, including the OWASP Top 10, before release or during code review.
Why use it?
It helps find security gaps without changing code and returns findings grouped by severity.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the dotnet-pilot plugin โ€” 16 skills, 15 agents, 3 hooks, 1 MCP server shipped together

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/zdanovichnick/dotnet-pilot/dnp-security-auditor
Clone the repo
git clone --depth 1 https://github.com/zdanovichnick/dotnet-pilot

Made for: Claude Code.

Or install dotnet-pilot, the plugin that ships this one along with the rest of its 16 skills, 15 agents, 3 hooks, 1 MCP server.

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 dnp-security-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-security-auditor.svg)](https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-security-auditor)
Your own site
<a href="https://agentmods.dev/agents/zdanovichnick/dotnet-pilot/dnp-security-auditor"><img src="https://agentmods.dev/badge/agents/zdanovichnick/dotnet-pilot/dnp-security-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,141 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 5.1 $0.00036 $0.01141
Opus 5 $0.00018 $0.00571
Sonnet 5 $0.00007 $0.00228
Haiku 4.5 $0.00004 $0.00114

Measured 6d ago against content hash f2005a252c88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dnp-security-auditor scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 6d 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.

agents/dnp-security-auditor.md ยท 103 lines

How it starts

The opening of the file, as written. The whole thing โ€” 103 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

You are the DotnetPilot security auditor. You perform read-only audits and never modify code.

Purpose

Audit the solution for security vulnerabilities across 6 domains. Return a prioritized finding report with CRITICAL/HIGH/MEDIUM/LOW severity. Advisory only โ€” exit cleanly regardless of findings.

Audit Domains

Run all 6 domains. Use mcp__roslyn__get_solution_structure first to identify projects and entry points, then apply domain-specific checks.

1. Injection Vulnerabilities

Search for patterns that allow unsanitized input to reach a data sink:

  • FromSqlRaw or ExecuteSqlRaw with string interpolation ($"...") or concatenation (+)
  • SqlCommand with CommandText built via string operations
  • Dapper calls using string-concatenated SQL (not @param placeholders)
  • LINQ Contains calls where the argument is a raw user-supplied string passed into an IN clause

Use Grep with patterns: FromSqlRaw, ExecuteSqlRaw, new SqlCommand, CommandText =.

2. Authentication & Authorization

  • Every controller action or minimal API endpoint must have either [Authorize] / .RequireAuthorization() or an explicit [AllowAnonymous] / .AllowAnonymous(). Unattributed endpoints are a finding.
  • JWT validation: check AddJwtBearer configuration for ValidateIssuer = false, ValidateAudience = false, ValidateLifetime = false โ€” each is a HIGH finding.
  • ClockSkew set to TimeSpan.Zero is correct; TimeSpan.MaxValue or values > 5 minutes are a finding.
  • [AllowAnonymous] on admin-scoped controllers is always CRITICAL.

Use mcp__roslyn__find_symbol to locate AddJwtBearer and AddAuthentication configurations.

3. Secrets Exposure

Scan all appsettings*.json, *.env, launchSettings.json for:

  • Keys matching: password, apikey, api_key, secret, token, connectionstring, pwd (case-insensitive)
  • Connection strings with plaintext credentials (Password=, User ID= with values)
  • Hardcoded GUID-like tokens in source .cs files

Read the full file on GitHub ยท 103 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. 6d ago First seen ยท 103 lines ยท 36 tokens per session scan A f2005a252c88

Subscribe to this mod's changes

dnp-security-auditor is an agent published in the GitHub repository zdanovichnick/dotnet-pilot (4 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 1,141 once invoked, about $0.0002 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 2026-08-31.