agent-skill-risk-scan

agent-skill-risk-scan is a skill for Claude Code, Codex from doteyeso-ops/mcp-server-vibes-coded. It costs 46 tokens per session (826 once invoked), scanned A, original, MIT.

A pre-installation security review for third-party agent skills, MCP plugins, packages, and installer commands. It statically checks their contents for risky behavior and returns a risk score and verdict.

In plain words
What is it for?
It helps review installation files and setup commands, find suspicious patterns, record a content fingerprint, and provide allow, review, or block guidance.
Why use it?
It helps identify supply-chain risks before unfamiliar code is installed or run, including secret access, unsafe commands, data collection, and destructive operations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit It helps review installation files and setup commands, find suspicious patterns, record a content fingerprint, and provide allow, review, or block guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doteyeso-ops/mcp-server-vibes-coded/agent-skill-risk-scan
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 doteyeso-ops/mcp-server-vibes-coded --skill agent-skill-risk-scan
Clone the repo
git clone --depth 1 https://github.com/doteyeso-ops/mcp-server-vibes-coded

Made for: Claude Code, Codex.

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 agent-skill-risk-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/doteyeso-ops/mcp-server-vibes-coded/agent-skill-risk-scan/github.svg)](https://agentmods.dev/skills/doteyeso-ops/mcp-server-vibes-coded/agent-skill-risk-scan)
Your own site
<a href="https://agentmods.dev/skills/doteyeso-ops/mcp-server-vibes-coded/agent-skill-risk-scan"><img src="https://agentmods.dev/badge/skills/doteyeso-ops/mcp-server-vibes-coded/agent-skill-risk-scan/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 agent-skill-risk-scan

Your own site · 80×15
<a href="https://agentmods.dev/skills/doteyeso-ops/mcp-server-vibes-coded/agent-skill-risk-scan"><img src="https://agentmods.dev/badge/skills/doteyeso-ops/mcp-server-vibes-coded/agent-skill-risk-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 826 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00046 $0.00826
Opus 5 $0.00023 $0.00413
Sonnet 5 $0.00009 $0.00165
Haiku 4.5 $0.00005 $0.00083

Measured 9d ago against content hash 45e37087f839, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-skill-risk-scan scanned grade A with 1 finding 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.

Makes network callslowCapability

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

curl -sS -X POST \
skills/agent-skill-risk-scan/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Skill Supply-Chain Risk Scan

Run this gate before installing or executing third-party agent skills, MCP plugins, package lifecycle scripts, or copied setup commands.

What it detects

  • downloaded content piped into a shell
  • private-key and credential-file references
  • secret-bearing environment-variable access
  • known external collection endpoints
  • operating-system command execution
  • destructive filesystem operations
  • encoded payload execution
  • automatic package lifecycle hooks

The result includes a 0–100 risk score, allow / review / block verdict, triggered rule IDs, evidence locations, SHA-256 content fingerprint, and remediation guidance.

This is deterministic static analysis. An allow result is not proof of provenance or safety.

Service listing: https://fiatdock.com/s/svc_119fd520-9e87-4b54-b73b-562968163805

Price: $0.05 USDC per scan on Base. FiatDock settles only after the seller returns an answer. A delivery failure is not charged unless the response explicitly contains a settled array.

Request a payment quote by posting the complete text as content:

curl -sS -X POST \
  https://fiatdock.com/s/svc_119fd520-9e87-4b54-b73b-562968163805 \
  -H 'Content-Type: application/json' \
  -d '{"content":"PASTE THE COMPLETE SKILL OR PLUGIN TEXT HERE"}'

The initial response is HTTP 402 and its accepts array lists every payment leg. Nothing is charged by the quote.

After signing each required Base USDC payment authorization, retry the identical request with PAYMENT-SIGNATURE. FiatDock x402 v2 expects a base64-encoded JSON array, one signed payload per accepted leg:

curl -sS -X POST \
  https://fiatdock.com/s/svc_119fd520-9e87-4b54-b73b-562968163805 \
  -H 'Content-Type: application/json' \
  -H 'PAYMENT-SIGNATURE: BASE64_JSON_ARRAY_OF_SIGNED_PAYLOADS' \
  -d '{"content":"PASTE THE COMPLETE SKILL OR PLUGIN TEXT HERE"}'

When multiple scanners disagree

Use the separate consensus service to reconcile two to ten reports from tools such as Snyk, Cisco Skill Scanner, Mondoo, or internal scanners:

Read the full file on GitHub · 78 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. 9d ago First seen · 78 lines · 46 tokens per session scan A 45e37087f839

Subscribe to this mod's changes

agent-skill-risk-scan is a skill published in the GitHub repository doteyeso-ops/mcp-server-vibes-coded (3 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 826 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

edgeone skill scanner

A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.

Tencent/AI-Infra-Guard · 148 tokens

create-custom-grader

Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.

NVIDIA/SkillEvaluator · 35 tokens

swiftui-expert-skill

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.

Agent-Threat-Rule/agent-threat-rules · 67 tokens

varlock-claude-skill

Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.

Agent-Threat-Rule/agent-threat-rules · 28 tokens

agent-safety

Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…

ericrisco/rsc-harness · 79 tokens

agoragentic-transaction-assurance

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…

rhein1/agoragentic-integrations · 65 tokens