auditing-skill-and-mcp-instructions

auditing-skill-and-mcp-instructions is a skill for Claude Code from UnboundCompute/security-agent-skills. It costs 147 tokens per session (1,628 once invoked), scanned A, original, MIT.

A security review tool for the written instructions that an AI agent reads, including skill descriptions, tool descriptions, parameter notes, comments, and markup.

In plain words
What is it for?
Use it before trusting a skill or MCP server, or when an agent behaves unexpectedly, to inspect the complete instruction text it receives.
Why use it?
Instruction text can influence an agent even when the program code is safe. Reviewing it helps find hidden text, misleading characters, or commands that try to override other instructions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the security-agent-skills plugin — 194 skills shipped together

Good fit Use it before trusting a skill or MCP server, or when an agent behaves unexpectedly, to inspect the complete instruction text it receives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions
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.

Any agent
npx skills add UnboundCompute/security-agent-skills --skill auditing-skill-and-mcp-instructions
Clone the repo
git clone --depth 1 https://github.com/UnboundCompute/security-agent-skills

Made for: Claude Code.

Or install security-agent-skills, the plugin that ships this one along with the rest of its 194 skills.

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 auditing-skill-and-mcp-instructions

README.md
[![agentmods](https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions/github.svg)](https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions)
Your own site
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions/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 auditing-skill-and-mcp-instructions

Your own site · 80×15
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-skill-and-mcp-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,628 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.
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 $0.00147 $0.01628
Opus 5 $0.00073 $0.00814
Sonnet 5 $0.00029 $0.00326
Haiku 4.5 $0.00015 $0.00163

Measured 11d ago against content hash c7edb200d044, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

auditing-skill-and-mcp-instructions 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 11d 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.

skills/auditing-skill-and-mcp-instructions/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditing skill and MCP instructions: the markdown is the attack surface

Most reviews read a skill or an MCP server as code and skim the prose. But the prose is what the model obeys. A skill body, a tool description, a parameter hint: the model reads all of it as instruction, not as documentation. That makes the instruction text a first-class injection surface, and it is the one almost every tool ignores because scanners lint code, not markdown. This skill lints the words.

When to use

  • You are reviewing a skill, an MCP server, or a marketplace entry before trusting it.
  • You want to know what instruction text will enter an agent's context on load.
  • You are triaging a skill that behaves in a way its visible instructions do not explain.

Scope check

Audit skills and servers you own or are authorized to review, on your own agent. Do not install untrusted artifacts outside a contained test. If you can't name the authorization, stop.

The loop

  1. Gather the full instruction surface as the model sees it. Collect every text the model actually reads: the skill body, the frontmatter description, each tool's name and description, parameter schemas and hints, and any prompt or context file the artifact loads. This is model input, not docs. Work from the exact bytes, not a rendered view.

  2. Normalize and reveal the hidden layers. Strip and expand markup so nothing stays folded: comments, collapsed regions, zero-size or off-screen text, and metadata a rendered view hides. Then scan the raw bytes for invisible and deceptive Unicode: zero-width characters, bidirectional overrides, tag characters, and homoglyphs that make one string read as another. Text a human never sees still reaches the model.

  3. Scan for override and role-spoofing instructions. Look for imperative text that countermands earlier guidance or impersonates a trusted voice: "ignore the previous instructions," "disregard the system prompt," "as the system," "you are now." Such text executes as an instruction the moment the artifact loads, with no call and no user request.

Read the full file on GitHub · 133 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. 11d ago First seen · 133 lines · 147 tokens per session scan A c7edb200d044

Subscribe to this mod's changes

auditing-skill-and-mcp-instructions is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 147 tokens to every session and 1,628 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

prodcheck-review

Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…

FarzamHabibi/pre-production-checklist · 70 tokens

integrate-arcjet-guard-genkit

Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 89 tokens

integrate-arcjet-guard-langgraph

Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…

arcjet/arcjet-js · 87 tokens

integrate-arcjet-guard-tanstack-ai

Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…

arcjet/arcjet-js · 103 tokens

integrate-arcjet-guard-claude-managed-agents

Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…

arcjet/arcjet-js · 102 tokens

linear-claude-skill

Manage Linear issues, projects, and teams.

Agent-Threat-Rule/agent-threat-rules · 15 tokens