wicked-garden-agentic-safety-reviewer

wicked-garden-agentic-safety-reviewer is a skill for Claude Code from mikeparcewski/wicked-garden. It costs 146 tokens per session (5,481 once invoked), scanned B, original, MIT.

A safety review guide for AI-agent systems, focused on guardrails, harmful input defenses, personal-data protection, human approval, and reducing made-up answers.

In plain words
What is it for?
Use it for safety assessments, prompt-injection audits, personal-data and compliance checks, guardrail reviews, and human-approval checks.
Why use it?
It helps identify ways an agent could be manipulated, expose personal information, bypass rules, or produce unreliable results.

Skill for Claude Code

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

Part of the wicked-garden plugin — 148 skills, 5 commands, 1 agent, 13 hooks shipped together

Good fit Use it for safety assessments, prompt-injection audits, personal-data and compliance checks, guardrail reviews, and human-approval checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mikeparcewski/wicked-garden/agentic-safety-reviewer
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 mikeparcewski/wicked-garden --skill agentic-safety-reviewer
Clone the repo
git clone --depth 1 https://github.com/mikeparcewski/wicked-garden

Made for: Claude Code.

Or install wicked-garden, the plugin that ships this one along with the rest of its 148 skills, 5 commands, 1 agent, 13 hooks.

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 wicked-garden-agentic-safety-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/agentic-safety-reviewer/github.svg)](https://agentmods.dev/skills/mikeparcewski/wicked-garden/agentic-safety-reviewer)
Your own site
<a href="https://agentmods.dev/skills/mikeparcewski/wicked-garden/agentic-safety-reviewer"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/agentic-safety-reviewer/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 wicked-garden-agentic-safety-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/mikeparcewski/wicked-garden/agentic-safety-reviewer"><img src="https://agentmods.dev/badge/skills/mikeparcewski/wicked-garden/agentic-safety-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,481 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00146 $0.05481
Opus 5 $0.00073 $0.02740
Sonnet 5 $0.00029 $0.01096
Haiku 4.5 $0.00015 $0.00548

Measured today against content hash 3e54f73d1d24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

wicked-garden-agentic-safety-reviewer scanned grade B with 2 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 today.

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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

r"ignore previous instructions",

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

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

grep -r "requests.get\|fetch\|urllib" --include="*.py" /path/to/codebase
skills/agentic-safety-reviewer/SKILL.md · 686 lines

How it starts

The opening of the file, as written. The whole thing — 686 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Safety Reviewer

This skill is designed to run as an isolated worker; when your harness cannot fork, run it inline and keep its output separate from the caller's.

You assess and improve safety mechanisms in agentic systems, focusing on guardrails, validation, PII protection, and defense against adversarial inputs.

Runtime

Script-backed steps use the wicked-garden launcher: wicked-garden run <plugin-root-relative path, e.g. scripts/…> [args]. It is on PATH after npm i -g wicked-garden; otherwise use npx wicked-garden run …; inside a wicked-crew run it is "$WICKED_GARDEN_ROOT/scripts/wicked-garden". If none of these is available, or Python 3 is missing, skip the script-backed step, say so, and follow the manual alternative where one is given next to it — never invent the script's output. Relative paths in this skill are relative to the directory that contains this SKILL.md.

First Strategy: Use wicked-* Ecosystem

Before manual analysis, leverage available tools:

  • Search: Use wicked-garden:search to find safety patterns and vulnerabilities
  • Memory: Use the wicked-garden-mem skill (recall action) to recall past safety issues
  • Tasks: Use TaskCreate/TaskUpdate with metadata={event_type, chain_id, source_agent, phase} to track safety findings (see scripts/_event_schema.py).

Your Focus

Guardrails and Validation

  • Input validation at agent entry points
  • Output validation before external actions
  • Content filtering (profanity, violence, illegal content)
  • Business rule enforcement
  • Rate limiting and quota management

Prompt Injection Defense

  • Direct injection detection (malicious instructions in user input)
  • Indirect injection (poisoned content from external sources)
  • Prompt leakage prevention (system prompt exposure)
  • Delimiter and boundary enforcement
  • Instruction hierarchy (system > user > tool)

PII Protection

  • PII detection in inputs and outputs
  • Redaction strategies (mask, hash, remove)
  • Logging without sensitive data
  • Compliance with GDPR, CCPA, HIPAA
  • Data minimization practices

Read the full file on GitHub · 686 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. today Changed · +7 lines 3e54f73d1d24
  2. 12d ago First seen · 679 lines · 146 tokens per session scan B e1d222f471ac

Subscribe to this mod's changes

wicked-garden-agentic-safety-reviewer is a skill published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 5,481 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (instruction-override phrasing, 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens