What is Patronus Security?

A local security tool for checking AI agents for prompt injection, personal-data leaks, and other data-loss risks. Prompt injection is text designed to trick an agent into ignoring its instructions.

It is for command-line scans and protection while an AI agent is running.

It helps find unsafe instructions and sensitive-data exposure before they affect an agent or leave the local environment.

Patronus Security — Agent for Claude Code by tenable

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.

Clone the repo

git clone --depth 1 https://github.com/tenable/cyberagents-exchange

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/tenable/cyberagents-exchange/patronus-security/github.svg)](https://agentmods.dev/agents/tenable/cyberagents-exchange/patronus-security)

Your own site

<a href="https://agentmods.dev/agents/tenable/cyberagents-exchange/patronus-security"><img src="https://agentmods.dev/badge/agents/tenable/cyberagents-exchange/patronus-security/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/tenable/cyberagents-exchange/patronus-security"><img src="https://agentmods.dev/badge/agents/tenable/cyberagents-exchange/patronus-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 818 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 unknown 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.

Model	Per session	Once invoked
Fable 5.1	$0.00027	$0.00818
Opus 5.5	$0.00011	$0.00327
Sonnet 5.5	$0.00005	$0.00164
Haiku 4.5	$0.00003	$0.00082

Measured 16d ago against content hash ac719d1299f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Patronus Security 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 16d 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.

Follow the [installation runbook](https://github.com/patronus-protect/patronus-security-cli/blob/main/INSTALL.md), including its checksum-first installation option, on macOS or Linux. The release installer requires `curl

agents/patronus-security.md · 44 lines

The source is not reproduced here

No licence file

Read it on GitHub

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.

16d ago First seen · 44 lines · 27 tokens per session scan A ac719d1299f2

Subscribe to this mod's changes

Patronus Security is an agent published in the GitHub repository tenable/cyberagents-exchange (23 stars, last pushed yesterday), with no licence file. It adds 27 tokens to every session and 818 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-21.

Building agents LLM Prompt Injection Security agentic-ai ai-agent-security ai-agents awesome-list claude cybersecurity dlp local-first mcp-security pii

Patronus Security next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Patronus Securitytenable/cyberagents-exchange	Agent	23	yesterday	none	A	27	Claude Code
Agent Prompt: Dream memory consolidationopenonion/connectonion	Agent	1.5k	yesterday	Apache-2.0	A	45	Claude Code
Agent Prompt: Session title and branch generationopenonion/connectonion	Agent	1.5k	yesterday	Apache-2.0	A	19	Claude Code
pre-explorerclosedloop-ai/claude-plugins	Agent	123	today	Apache-2.0	A	48	Claude Code
amend-extractorclosedloop-ai/claude-plugins	Agent	123	today	Apache-2.0	A	23	Claude Code
language-detectorclosedloop-ai/claude-plugins	Agent	123	today	Apache-2.0	A	12	Claude Code
api-spec-writerclosedloop-ai/claude-plugins	Agent	123	today	Apache-2.0	A	31	Claude Code

Patronus Security

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

The source is not reproduced here

No licence file

What this file has done since we first saw it

Patronus Security compared with agents from other repositories