pentest-agents-mistakes

pentest-agents-mistakes is a cursor rule for Cursor from H-mmer/pentest-agents. It costs 7 tokens per session (17,584 once invoked), scanned A, original, no licence file.

A running record of mistakes made during security testing, with lessons that apply across different programs.

In plain words
What is it for?
Reviewing past testing failures before starting new security assessments.
Why use it?
It helps agents avoid repeating wasted work, overstated findings, missed bugs, and corrections from users.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Reviewing past testing failures before starting new security assessments.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/h-mmer/pentest-agents/pentest-agents-mistakes
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/H-mmer/pentest-agents

Made for: Cursor.

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 pentest-agents-mistakes

README.md
[![agentmods](https://agentmods.dev/badge/rules/h-mmer/pentest-agents/pentest-agents-mistakes/github.svg)](https://agentmods.dev/rules/h-mmer/pentest-agents/pentest-agents-mistakes)
Your own site
<a href="https://agentmods.dev/rules/h-mmer/pentest-agents/pentest-agents-mistakes"><img src="https://agentmods.dev/badge/rules/h-mmer/pentest-agents/pentest-agents-mistakes/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 pentest-agents-mistakes

Your own site · 80×15
<a href="https://agentmods.dev/rules/h-mmer/pentest-agents/pentest-agents-mistakes"><img src="https://agentmods.dev/badge/rules/h-mmer/pentest-agents/pentest-agents-mistakes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 17,584 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00007 $0.17584
Opus 5 $0.00003 $0.08792
Sonnet 5 $0.00001 $0.03517
Haiku 4.5 $0.00001 $0.01758

Measured 6d ago against content hash ebba61c3d5da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pentest-agents-mistakes scanned grade A 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 6d 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.

Asks the agent to reveal its instructionslowSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

Why: Direct requests ("output your system prompt", role-play, translation, base64) trigger "never reveal" guardrails. Techniques that never mention the prompt work because the model doesn't know it's being extracted.

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.

4. **Use a real browser for WAF/JS/CAPTCHA/UI-mediated bugs.** `curl` 403 from a CDN is not "not vulnerable" — it's "you never reached the app."
providers/cursor/.cursor/rules/pentest-agents-mistakes.mdc · 693 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

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.

  1. 6d ago First seen · 693 lines · 7 tokens per session scan A ebba61c3d5da

Subscribe to this mod's changes

pentest-agents-mistakes is a cursor rule published in the GitHub repository H-mmer/pentest-agents (836 stars, last pushed 2mo ago), with no licence file. It adds 7 tokens to every session and 17,584 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 2 findings (asks the agent to reveal its instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.