Skip to content
New

DeepSeek V4.1 Flash free for 7 days: 10M tokens a day after a top-up of $10 or more. Until Nov 30.

How it works
noorqureshi/ai-agent-tool-abuseAI, agents and MCP

ai-agent-tool-abuse

⁨Abuse an LLM agent's tools/functions — coerce it to call tools with attacker-chosen args for SSRF, RCE, data exfil, or privilege abuse. Load when the target is an agent with tools/ function-calling/plugins, MCP servers, code interpreters, or "the assistant can do X". Signals: function-calling, tool ⁩

v2026.10.14-ee0e0c53 installs+3 in 7 days27 StarsMITsynced 22 hours ago

Install

No NotHoly CLI yet? Install it first.

$ curl -fsSL https://notholy.com/install.sh | sh
$ notholy skills install noorqureshi/ai-agent-tool-abuse

Writes to ⁦~/.notholy/skills⁩ after checking the signature and the SHA-256.

SignatureSigned, ed25519
1ke0HpYyL7…wNUzFbDw==The CLI checks the SHA-256 and the signature before it writes a file.
Packageb6fe48c7…946d752c
b6fe48c70192…3cce946d752c1 file · ⁦1.5 KB⁩
ScanLowno findings
The scan found nothing to flag in this version.See the full scan
Sourcegithub.com/NoorQureshi/security-skills/tree/main/skills/ai-ml/ai-agent-tool-abuse@ee0e0c5

When it applies

The target isn't just a chatbot — it can act: call functions, browse, run code, query databases, send email, hit internal APIs, or chain MCP tools. Impact jumps from "bad text" to real actions taken with the agent's privileges.

Why it works

The model decides which tool to call and with what arguments, driven by text it can't fully trust (user input or fetched content). If tools are over-permissioned or arguments aren't validated, attacker text steers real actions — the classic "confused deputy".

Method

  1. Enumerate the tools: get the agent to reveal its tools/functions and schemas (often it just lists them), or read the app/MCP config.
  2. Coerce a call (direct or via ai-prompt-injection/ai-rag-poisoning): craft input so the agent invokes a tool with your arguments.
  3. Route to impact:
    • SSRF/internal reach: a browse/fetch tool → internal URLs, cloud metadata (→ cloud-imds-ssrf).
    • RCE: a code-interpreter/shell tool → command execution.
    • Data exfil: a query/email/file tool → dump data to you (markdown-image beacon, an email to your address).
    • Privilege abuse: an admin/action tool called on behalf of a victim (confused deputy).
  4. Chaining: poisoned content the agent reads later triggers the tool call (indirect, multi-user).

Gotchas

  • The severity is the action, tied to the tool's real privilege — demonstrate the effect, not just intent.
  • Guardrails on the model don't cover tool arg-validation — the bug is often at the tool boundary.
  • Defenders: least-privilege tools, human-in-the-loop for sensitive actions, validate/allowlist args, isolate the browser/exec.

Verify success

The agent performs an attacker-directed action via a tool — an SSRF hit, code execution, data exfiltrated, or a privileged action taken — traceable to your input.

References

OWASP LLM Top 10 (2025) LLM06/LLM01; MCP security guidance; agent "confused deputy" research.

Files in this version

Permissions

PermissionDeclaredFound by the scan
Reads filesNoNo
Writes filesNoNo
Runs shell commandsNoNo
Uses the networkNoNo
Uses connectorsNoNo
Drives a browserNoNo

Scan findings

Reviewed on Nov 13, 2026

The scan found nothing to flag in this version.

A clean scan lowers the risk but does not prove a package is safe. Read what you install.

VersionPublishedCommitSHA-256SignaturePermission change
v2026.10.14-ee0e0c5Nov 13, 2026ee0e0c5b6fe48c7Signed–

Ask anything your scope allows.

Create an account, add credits and ask the first question in the chat or the terminal.

  1. 1/3

    Create the account

    Individual or company. You can switch to a company later without losing balance or keys.

    IndividualCompany
  2. 2/3

    Add credits

    By card. Pay per token, no subscription.

    $5.00minimum deposit
  3. 3/3

    Ask

    In the chat, or install the CLI and run notholy login in your terminal.

    $ notholy login