security-scanning

security-scanning is a skill for Claude Code from a5c-ai/babysitter. It costs 26 tokens per session (454 once invoked), scanned A, original, MIT.

A security auditing tool for finding exposed secrets, unsafe permissions, risky code hooks, tool-connection risks, and problems in agent configuration. It can also perform an optional red-team simulation, which imitates attacks to expose weaknesses.

In plain words
What is it for?
Use it to scan source and configuration files, review filesystem and network access, inspect hooks and MCP tools, and check agent prompts and output handling.
Why use it?
It helps identify credentials, unsafe execution paths, excessive permissions, and prompt-injection or data-leak risks before they cause harm.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Good fit Use it to scan source and configuration files, review filesystem and network access, inspect hooks and MCP tools, and check agent prompts and output handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a5c-ai/babysitter/security-scanning
About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,788 stars · on GitHub · a5c.ai

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 a5c-ai/babysitter --skill security-scanning
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Made for: Claude Code.

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 security-scanning

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/security-scanning/github.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/security-scanning)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/security-scanning"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/security-scanning/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 security-scanning

Your own site · 80×15
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/security-scanning"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/security-scanning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 454 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Tool Misuse · line 27
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
How audits are shown
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 $0.00026 $0.00454
Opus 5 $0.00013 $0.00227
Sonnet 5 $0.00005 $0.00091
Haiku 4.5 $0.00003 $0.00045

Measured 9d ago against content hash 97a787c89ddf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

security-scanning 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.

Runs shell commandslowCapability

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

- Process execution (child_process)
library/methodologies/everything-claude-code/skills/security-scanning/SKILL.md · 67 lines

What it actually says

  • AWS access keys (AKIA pattern)
  • GitHub tokens (ghp_, gho_, ghs_, ghr_)
  • Generic API keys and bearer tokens
  • Database connection strings with credentials
  • Private keys (RSA, EC, SSH)
  • JWT secrets and signing keys
  • OAuth client secrets
  • Slack tokens and webhooks
  • Cloud provider credentials (GCP, Azure)

2. Permission Auditing

  • File system read/write scope
  • Network calls and protocols
  • Process execution (child_process)
  • File permissions (777, world-writable)
  • CORS and CSP headers
  • Docker privilege escalation

3. Hook Injection Analysis

  • Git hooks for command injection
  • npm lifecycle scripts (preinstall, postinstall)
  • Claude Code hooks for unsafe patterns
  • eval()/Function()/dynamic code execution
  • Unvalidated user input in shell commands

4. MCP Risk Profiling

  • Tool permission inventory
  • Data exposure risk mapping
  • Transport security (stdio vs SSE vs HTTP)
  • Prompt injection via tool descriptions
  • Rate limiting verification

5. Agent Config Review

  • Model settings integrity
  • Prompt injection resistance
  • Tool allowlist scoping
  • Output validation and sanitization
  • Information leakage in error messages

Optional: Red Team Simulation

  • Attack simulation against found vulnerabilities
  • Exploitability rating: trivial, moderate, difficult, theoretical
  • Blue-team defense recommendations

When to Use

  • Pre-deployment security review
  • New dependency introduction
  • Hook or plugin configuration changes
  • Agent or MCP server setup

Agents Used

  • security-reviewer (primary consumer)
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 67 lines · 26 tokens per session scan A 97a787c89ddf

Subscribe to this mod's changes

security-scanning is a skill published in the GitHub repository a5c-ai/babysitter (1,788 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 454 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.