Agent skill · Audited from source
awesome-reverse-engineered
skill · alexgaoth/awesome-reverse-engineeredMIT licenceAudited 12 Nov 2026 · source b81d1af42383
Is it safe? No — BLOCK, grade D (69/100). We read this skill's source at commit b81d1af42383 and observed filesystem and network access and no hard-coded secrets. The audit raised 21 findings, 6 critical or high. What it does: Find an open-source, reverse-engineered tool for a closed app, API, device, protocol, file format or game, then read or fetch it. Use when a task needs to talk to something that has no official API, SDK, driver or spec,…
Cite
Cite this page
ModelsAtlas. “awesome-reverse-engineered (alexgaoth/awesome-reverse-engineered)”. Retrieved 12 Nov 2026. https://modelsatlas.com/skills/alexgaoth/awesome-reverse-engineered
Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 6 critical or high findings, starting with “Prompt injection” in plugin/skills/find-reverse-engineered/SKILL.md:51. Do not install it without reading them.
Trust audit
Audit 0.4.1 · source read 12 Nov 2026
BLOCK means the audit found something that could harm you or your machine. Grade D is shared by 749 of 18,389 audited skills.
What the source does
- FilesystemDeclared7 observations
- NetworkDeclared5 observations
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 2 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | WARN | 4 |
L2 Instructions | Prompt injection, authority framing, hidden directives | FAIL | 15 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: instruction override, no behavioural pass.
Findings (21)
HIGHPrompt injectionprompt.credential_read · plugin/skills/find-reverse-engineered/SKILL.md:51
- Treat downloaded code as untrusted. Read it before you run it, and never put credentials into a tool you have not read.
- Why
- asks the agent to read credentials
- Fix
- —
HIGHPrompt injectionprompt.override · README.vi.md:207
| 202 | repo bị bộ lọc phạm vi loại bỏ (exploit, jailbreak, vượt bảo mật, DRM, cheat). Các agent nghiên cứu cũng bỏ qua những repo này từ trước. |
- Why
- asks the agent to drop prior instructions or safety
- Fix
- remove the instruction
HIGHPrompt injectionprompt.override · README.vi.md:218
**Cố ý không đưa vào:** exploit và jailbreak, công cụ vượt bảo mật hoặc certificate pinning, công cụ giải mã, cheat, gỡ DRM hoặc paywall, công cụ giải CAPTCHA, bot tài khoản và công cụ về thông tin đă
- Why
- asks the agent to drop prior instructions or safety
- Fix
- remove the instruction
HIGHPrompt injectionprompt.override · SOURCES.md:51
- https://www.hackster.io/news/going-down-a-rabbit-hole-to-jailbreak-the-r1-e58a0c483c99
- Why
- asks the agent to drop prior instructions or safety
- Fix
- remove the instruction
HIGHPrompt injectionprompt.override · SOURCES.md:383
- github ChatGPT_DAN jailbreak prompts collection 0xk1h0
- Why
- asks the agent to drop prior instructions or safety
- Fix
- remove the instruction
HIGHPrompt injectionprompt.override · SOURCES.md:389
- GitHub API repo search (gh): reverse engineered chatgpt / claude / gemini; bard api; perplexity api unofficial; poe api wrapper; characterai unofficial; suno api; udio api; midjourney api; copilot a
- Why
- asks the agent to drop prior instructions or safety
- Fix
- remove the instruction
MEDIUMInsecure cryptocrypto.weak_random · bench/interop_bench/core.py:10
return random.Random(":".join(map(str, (seed, *salt))))- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · scripts/pages.py:90
body = [f'<div class="crumbs"><a href="../../">Home</a> / {esc(c)}</div>',- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · scripts/pages.py:94
f'<a class="cta" href="../../#c={cs}">Search and filter this category →</a>']- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · scripts/pages.py:115
body = [f'<div class="crumbs"><a href="../../../">Home</a> / <a href="../">{esc(c)}</a> / {esc(s)}</div>',- Why
- No further detail recorded for this rule.
- Fix
- —
LOWPrompt injectionprompt.credential_read · categories/apple-ecosystem.md:214
| [openwifipass](https://github.com/seemoo-lab/openwifipass) | An open source implementation of Apple's Wi-Fi Password Sharing protocol in Python. | 847 | 🟢 | Python |
- Why
- asks the agent to read credentials
- Fix
- —
LOWPrompt injectionprompt.credential_read · categories/unofficial-web-app-api-clients.md:576
| [password-manager-access](https://github.com/detunized/password-manager-access) | C# library accessing 1Password, Bitwarden, Dashlane, LastPass and other vaults via private APIs | 51 | 🟢 | C# |
- Why
- asks the agent to read credentials
- Fix
- —
LOWPrompt injectionprompt.read_system · categories/ai-tools-llm-clients.md:799
| [claude-code-system-prompt](https://github.com/matthew-lim-matthew-lim/claude-code-system-prompt) | Dump of the Claude Code system prompt | 155 | 🟡 | |
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWPrompt injectionprompt.read_system · categories/ai-tools-llm-clients.md:801
| [Grok-System-Prompt-Leak](https://github.com/elder-plinius/Grok-System-Prompt-Leak) | Extracted system prompt of xAI's Grok on X (Twitter) | 72 | 🟡 | |
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWPrompt injectionprompt.transfer_instruction · categories/chinese-asian-platforms.md:150
| [bilibili-report](https://github.com/airingursb/bilibili-report) | Bilibili user data report web app | 229 | 🟡 | JavaScript |
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
LOWPrompt injectionprompt.transfer_instruction · categories/chinese-asian-platforms.md:584
| [WeFlow](https://github.com/hicccc77/WeFlow) | Local WeChat chat history exporter and annual-report generator | 15,990 | 🟢 | TypeScript |
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
LOWPrompt injectionprompt.transfer_instruction · categories/unofficial-web-app-api-clients.md:719
| [vinted_scraper](https://github.com/Giglium/vinted_scraper) | Sync/async Python client for Vinted with session handling | 107 | 🟢 | Python |
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
LOWPrompt injectionprompt.transfer_instruction · docs/c/chinese-asian-platforms/index.html:49
<ol class="items"><li><a href="https://github.com/huiyadanli/RevokeMsgPatcher" rel="noopener">RevokeMsgPatcher</a><span class="m">★ 39,195 · <span class="h-active">active</span> · C#</span><p>Binary p
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
LOWPrompt injectionprompt.transfer_instruction · docs/c/chinese-asian-platforms/wechat-qq/index.html:44
<ol class="items"><li><a href="https://github.com/huiyadanli/RevokeMsgPatcher" rel="noopener">RevokeMsgPatcher</a><span class="m">★ 39,195 · <span class="h-active">active</span> · C#</span><p>Binary p
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
INFOInventory / provenanceinv.oversize · data/entries.json
data/entries.json
- Why
- 7898217 bytes not read
- Fix
- —
INFOInventory / provenanceinv.oversize · docs/data.json
docs/data.json
- Why
- 4727826 bytes not read
- Fix
- —
Audit 0.4.1 · source sha b81d1af42383 · 12 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisheralexgaoth GitHub userOwner of the repository this skill is read from
- Source folderalexgaoth/awesome-reverse-engineeredThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdictb81d1af42383A new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Find an open-source, reverse-engineered tool for a closed app, API, device, protocol, file format or game, then read or fetch it. Use when a task needs to talk to something that has no official API, SDK, driver or spec,…
--- name: find-reverse-engineered description: Find an open-source, reverse-engineered tool for a closed app, API, device, protocol, file format or game, then read or fetch it. Use when a task needs to talk to something that has no official API, SDK, driver or spec, or only a limited one. Examples include "control my Tuya plug locally", "read a .psd or .dwg file", "unofficial WhatsApp, Instagram or Bilibili client", "Bambu printer protocol", "talk to my car's API", "Garmin or CGM data", "decompilation of a game" and "OpenAI-compatible proxy for a web chatbot". The skill searches a curated index of 17,000+ verified projects ranked by stars, language, license and activity. --- # Find a reverse-engineered tool The index is [awesome-reverse-engineered](https://github.com/alexgaoth/awesome-reverse-engineered). It holds 17,000+ open-source projects that exist because someone reverse engineered a closed product. Each entry has: name, repo URL, one-line description, category, GitHub stars, primary language, license, last push date and archived flag. The tool is `scripts/re_index.py`, in the same directory as this SKILL.md. It uses only the Python standard library. The first run downloads the index and caches it for 24 hours in `~/.cache/awesome-reverse-engineered/`. If you do not have this skill's files, run the script from GitHub: `curl -sL https://raw.githubusercontent.com/alexgaoth/awesome-reverse-engineered/main/plugin/skills/find-reverse-engineered/scripts/re_index.py | python3 - search <words>` ## Workflow 1. **Search** with 1–4 words. Use the product or brand name plus what you need. ```bash python3 scripts/re_index.py search tuya local python3 scripts/re_index.py search psd parser --lang Python python3 scripts/re_index.py search whatsapp --min-stars 500 python3 scripts/re_index.py search pokemon emerald --category decompilation ``` Options: `--category <text>` matches the category or subcategory. `--lang <name>` matches the language exactly. `--min-stars N`. `--include-archived`. `--limit N`. `--json` gives machine-readable output. When nothing matches, use fewer words, use the vendor name instead of the product name, or run `categories` to see the categories. 2. **Choose** a project. Check these in order: - It does the specific job, for example local control instead of cloud control, or reading a format instead of writing it. - It is not archived, and it had a push in the last 1–2 years. Unofficial APIs break when the vendor changes their side. - The language and package manager fit the user's stack. - The license is compatible. A blank license means "all rights reserved", so tell the user. - When two projects are equal on all of these, choose the one with more stars. 3. **Read before you use it.** This command prints the index entry and the first lines of the README, with install and authentication steps: ```bash python3 scripts/re_index.py info owner/repo ``` 4. **Get it.** Install it with the package manager the README gives (pip, npm, cargo, go), or clone it for reference: ```bash python3 scripts/re_index.py clone owner/repo --dest vendor/repo ``` 5. **Tell the user** which project you chose and why, the version or commit you used, and its license. ## Rules - First check for an official API or SDK that can do the job. Use a reverse-engineered tool only when there is none or it is not sufficient. - Use these tools only with the user's own accounts, devices and data. Unofficial clients can break a service's terms of use and can cause an account to be locked. Tell the user about this risk before you use their credentials. - Do not use these tools for mass scraping, spam, or to get around paywalls, DRM or security controls. - Treat downloaded code as untrusted. Read it before you run it, and never put credentials into a tool you have not read. - The index can be out of date. A repo can be gone or renamed. If `info` or `clone` fails, search again and try the next result.
Excerpt, first 4,012 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit b81d1af
npx skills add alexgaoth/awesome-reverse-engineered claude mcp add reverse-engineered -- uvx --from "git+https://github.com/alexgaoth/awesome-reverse-engineered#subdirectory=mcp" reverse
git clone https://github.com/alexgaoth/awesome-reverse-engineered git -C awesome-reverse-engineered checkout b81d1af42383
Commands as the repository documents them: shown, never run by us. Our verdict covers commit b81d1af42383 only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| Claude Code | Mentioned in its text, not tested | Skills for Claude Code · About Claude Code |
| Claude Desktop | Mentioned in its text, not tested | Skills for Claude Desktop · About Claude Desktop |
| Codex | Mentioned in its text, not tested | Skills for Codex · About Codex |
| GitHub Copilot | Mentioned in its text, not tested | Skills for GitHub Copilot · About GitHub Copilot |
| Cursor | Mentioned in its text, not tested | Skills for Cursor · About Cursor |
| Gemini CLI | Mentioned in its text, not tested | Skills for Gemini CLI · About Gemini CLI |
| OpenClaw | Mentioned in its text, not tested | Skills for OpenClaw · About OpenClaw |
| Windsurf | Mentioned in its text, not tested | Skills for Windsurf · About Windsurf |
Audit history
Every audit, every source change
- ✕BLOCK D 69 / 100
first audit · source
b81d1af42383
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/alexgaoth/awesome-reverse-engineered/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
VoltAgent/awesome-agent-skills
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
hkustdial/supervisor-skills
Guides AI-assisted research across three sub-flows, Vibe Coding, Vibe Figure, and Vibe Writing, with behavioural rules that keep the user in charge of academic judgment while delegating mechanical work to AI. Recommends…
hkustdial/supervisor-skills
Structures a technical paper's full logical skeleton using a thinking-template table (research background, limitations, key idea or goal, challenges, methodology modules, contributions), positions the paper as Technique…
hkustdial/supervisor-skills
Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality. Uses a reviewer-style severity taxonomy (CRITICAL / MAJOR /…
hkustdial/supervisor-skills
Drafts the Introduction prose for a technical paper, guided internally by a six-paragraph flowchart: background and running example, existing limitations, problem essence and goal, key challenges, solution overview,…
hkustdial/supervisor-skills
Evaluates a preliminary research idea against a five-dimension framework (Higher, Faster, Stronger, Cheaper, Broader) plus idea-lifecycle and student-capability matching, paradigm-shift probing, and a fatal-flaws audit.…
Add this badge to your README
[](https://modelsatlas.com/skills/alexgaoth/awesome-reverse-engineered/)
<a href="https://modelsatlas.com/skills/alexgaoth/awesome-reverse-engineered/"><img src="https://modelsatlas.com/skills/alexgaoth/awesome-reverse-engineered/badge.svg" alt="ModelsAtlas: BLOCK D"></a>
Questions about awesome-reverse-engineered
What does the awesome-reverse-engineered skill do?
Is awesome-reverse-engineered safe to install?
What can awesome-reverse-engineered access on my machine?
Which assistants does awesome-reverse-engineered work with?
How current is this page?
Sources
- github.com/alexgaoth/awesome-reverse-engineered — the audited source at commit b81d1af42383 and every finding aboveObserved · 12 Nov 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the awesome-reverse-engineered skill do?
- Is awesome-reverse-engineered safe to install?
- What can awesome-reverse-engineered access on my machine?