fire-security-scan

A security-check command for inspecting agent add-ons, tools, documents, and code for unsafe instructions or behavior.

In plain words
What is it for?
Use it to scan a file, folder, URL, tool collection, skills library, plugins, or documents.
Why use it?
It helps find prompt injection, personal-data collection, stolen credentials, and malicious software before they enter or affect a system.

Command

Part of the fire-flow plugin — 44 commands, 15 agents 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 commands/thierryn/fire-flow/fire-security-scan
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow

Or install fire-flow, the plugin that ships this one along with the rest of its 44 commands, 15 agents.

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,263 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 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 $0.00025 $0.04263
Opus 5 $0.00013 $0.02132
Sonnet 5 $0.00005 $0.00853
Haiku 4.5 $0.00003 $0.00426

Measured 3d ago against content hash 3d341ae98193, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

fire-security-scan scanned grade C with 3 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 3d 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.

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.

2. Does it try to override safety instructions?

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

Harvests environment variablesmediumData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

After the OpenClaw/ClawdBot attack (2025) where malicious skill instructions told the AI to collect API keys and crypto wallets at 2 AM and mail them to a hacker, this command provides a mandatory security gate for anyth

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.

- curl, wget, fetch references in non-code-execution contexts
commands/fire-security-scan.md · 484 lines

How it starts

The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fire-security-scan

Inspect any skill, plugin, MCP tool, RAG document, or code for malicious instructions, prompt injection, PII harvesting, credential theft, and supply chain attacks.


Purpose

After the OpenClaw/ClawdBot attack (2025) where malicious skill instructions told the AI to collect API keys and crypto wallets at 2 AM and mail them to a hacker, this command provides a mandatory security gate for anything that enters our system.

OWASP Agentic Top 10 (2026) coverage:

  • ASI01: Agent Goal Hijacking (prompt injection in skills/tools)
  • ASI04: Supply Chain Vulnerabilities (malicious plugins/MCP servers)
  • ASI06: Memory/Context Poisoning (RAG document injection)
  • ASI10: Rogue Agents (instructions that create exfiltration behavior)

Arguments

arguments:
  target:
    required: false
    type: string
    description: "File path, directory, or URL to scan"
    example: "/fire-security-scan ~/.claude/plugins/some-plugin/skills/new-skill.md"

optional_flags:
  --mcp-tools: "Scan all loaded MCP tool descriptions"
  --all-skills: "Scan entire skills library"
  --all-plugins: "Scan all installed plugin files"
  --rag-docs: "Scan directory of documents before RAG ingestion"
  --deep: "Include AI-powered intent classification (slower, more thorough)"
  --fix: "Auto-strip detected invisible characters and sanitize"
  --report: "Save full report to .planning/security/"

Process

Step 1: Determine Scan Target

+------------------------------------------------------------------------------+
|                    POWER SECURITY SCAN                                        |
+------------------------------------------------------------------------------+
|                                                                              |
|  Target: {file/directory/--flag}                                             |
|  Mode: {quick | deep}                                                        |
|  Scan Layers: 6                                                              |
|                                                                              |
+------------------------------------------------------------------------------+

Read the full file on GitHub · 484 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. 3d ago First seen · 484 lines · 25 tokens per session scan C 3d341ae98193

Subscribe to this mod's changes

fire-security-scan is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 21d ago), licensed MIT. It adds 25 tokens to every session and 4,263 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 3 findings (instruction-override phrasing, harvests environment variables, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.