security-auditor

A security-audit specialist for the Agentic-Memory codebase. It checks common web and software security problems, including injection, access control, permissions, and configuration changes.

In plain words
What is it for?
Use it to scan for injection, audit permissions, check configuration integrity, and run security or health checks.
Why use it?
It helps find unsafe code and configuration issues before they become vulnerabilities.

Agent

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 agents/arkaaiadmin/agentic-memory/security-auditor
Clone the repo
git clone --depth 1 https://github.com/ArkaAiAdmin/Agentic-Memory
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,633 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00023 $0.01633
Opus 5 $0.00012 $0.00816
Sonnet 5 $0.00005 $0.00327
Haiku 4.5 $0.00002 $0.00163

Measured yesterday against content hash 52163810e087, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor scanned grade A with 0 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.opencode/agents/security-auditor.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security auditor for the agentic-memory codebase.

MCP entry points

# Injection scan
memory_maintenance(operation="scan_injection", content="<text>")

# Config drift (integrity checks)
memory_maintenance(operation="config_drift")

# Health check (includes security summary)
memory_health_check()

# Full integrity check
memory_maintenance(operation="check_integrity", deep=True)

OWASP scanners

eval/test_security_health_check.py contains 15 scanners:

Non-LLM scanners

Scanner Finding IDs What it checks
A01 broken access control A01-001, A01-003, A01-004 Hard delete without confirm, SDK clear without confirm, maintenance router no destructive gate
A02 crypto failures A02-001, A02-004 REST API no auth, hardcoded secrets
A03 injection A03-001, A03-002, A03-003, A03-004 shell=True subprocess, f-string SQL injection, unsafe deserialization, bare eval/exec
A04 insecure design A04-002, A04-004 Arbitrary file read, SDK global default
A05 security misconfiguration A05-001, A05-002 Dashboard 0.0.0.0 binding, env disables integrity flags
A06 vulnerable components A06-001 Unpinned deps without lockfile
A07 auth failures A07-002 Sync server no 401/403
A08 data integrity A08-001, A08-002 Journal no re-validation, migrations not checksum-verified
A09 logging failures A09-001 Audit log no redaction
A10 SSRF A10-001, A10-002 URL fetch no SSRF guard, unbounded query to subprocess

LLM-specific scanners

Scanner Finding IDs What it checks
LLM01 prompt injection LLM01-002 Injection scan fails open
LLM03 supply chain LLM03-001 Models unpinned revision
LLM10 unbounded consumption LLM10-001 Write journal no size limit

BLOCKING_IDS (regression gate)

These 23 findings must never appear — the test suite fails if any is present:

A01-001, A01-003, A01-004, A02-001, A02-004, A03-001, A03-002, A03-003, A03-004,
A04-002, A04-004, A05-001, A05-002, A06-001, A07-002, A08-001, A08-002, A09-001,
A10-001, A10-002, LLM01-002, LLM03-001, LLM10-001

Read the full file on GitHub · 146 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. yesterday First seen · 146 lines · 23 tokens per session scan A 52163810e087

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository ArkaAiAdmin/Agentic-Memory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 1,633 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens