Password Field Security
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing headers, forms, cookies, or third-party integrations related to Secure password input fields.
Find compromised passwords in the user's personal accounts, prepare official reset flows, hand over before the user enters and submits each new credential, and help verify the change and authorized…
CC0-1.0Auto-check passed
Install Secure Me
$ npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install asgeirtj/system_prompts_leaks secure-me --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/OpenAI/dots/skills/secure-me .claude/skills/secure-me && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "secure-me" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/secure-me into .claude/skills/secure-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "secure-me", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/secure-meType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install asgeirtj/system_prompts_leaks secure-me --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .agents/skills && cp -r skills-src/OpenAI/dots/skills/secure-me .agents/skills/secure-me && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "secure-me" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/secure-me into .agents/skills/secure-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "secure-me", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install asgeirtj/system_prompts_leaks secure-me --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/OpenAI/dots/skills/secure-me .cursor/skills/secure-me && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "secure-me" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/secure-me into .cursor/skills/secure-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "secure-me", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/asgeirtj/system_prompts_leaks.git --path OpenAI/dots/skills/secure-me--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install asgeirtj/system_prompts_leaks secure-me --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/OpenAI/dots/skills/secure-me .gemini/skills/secure-me && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "secure-me" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/secure-me into .gemini/skills/secure-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "secure-me", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install asgeirtj/system_prompts_leaks secure-meInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .github/skills && cp -r skills-src/OpenAI/dots/skills/secure-me .github/skills/secure-me && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "secure-me" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/secure-me into .github/skills/secure-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "secure-me", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install asgeirtj/system_prompts_leaks secure-me --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/OpenAI/dots/skills/secure-me .opencode/skills/secure-me && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "secure-me" agent skill from https://github.com/asgeirtj/system_prompts_leaks/tree/main/OpenAI/dots/skills/secure-me into .opencode/skills/secure-me/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "secure-me", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
secure-me- GitHub stars
- 69k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 789 words
- Files
- 1
- Skills in repo
- 128
- Repo updated
- First seen
- Licence
- CC0-1.0
At a glance
Find compromised passwords in the user's personal accounts, prepare official reset flows, hand over before the user enters and submits each new credential, and help verify the change and authorized…
- SKILL.md covers Find compromised passwords, Prepare the change and hand over, Verify and finish and Examples
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Secure Me is an agent skill from asgeirtj/system_prompts_leaks. Find compromised passwords in the user's personal accounts, prepare official reset flows, hand over before the user enters and submits each new credential, and help verify the change and authorized password-manager save.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro… The licence is CC0-1.0.
Example prompts
- “/secure-me”
What it can do on your machine
Read from SKILL.md and the folder at commit 60d44cc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Secure Me loads about 1.3k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 789 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from asgeirtj/system_prompts_leaks at commit 60d44cc, republished under its CC0-1.0 licence (© asgeirtj). 789 words, ~1,321 tokens.
Download SKILL.mdSave it as
.claude/skills/secure-me/SKILL.md (or your agent's skills folder).- name
- secure-me
- description
- Find compromised passwords in the user's personal accounts, prepare official reset flows, hand over before the user enters and submits each new credential, and help verify the change and authorized password-manager save.
dot Secure Me
Find exposed passwords, prepare each provider's official reset flow, and help the user verify what was changed and saved. The user enters, confirms, and submits every new credential.
Find compromised passwords
- Start with the chosen password manager, such as Chrome, and check its current security report and what the available tools can inspect. Use the user's existing account choices and connections. Report which accounts were covered and any gaps.
- Look for a current compromised-password warning, a verified provider notice, or a disclosure the user confirms. Check whether the warning concerns an old vault entry or a password already changed. An email address in an old breach is not enough to conclude that the current password was exposed. Separate confirmed and uncertain findings.
- Include other accounts the manager reports as using the same exposed password, without extracting or comparing secret values. Missing, weak, or reused passwords alone are outside this cleanup. Start with compromised email, identity-provider, and password-manager accounts that could unlock others, then financial and other sensitive accounts.
Prepare the change and hand over
- If the user asked for a check, report affected accounts and explain the next step. If they asked for help fixing them, prepare the official flow account by account. Follow
<confirmation_policy>: ask the user to take over before any new credential is entered. The user must enter it, confirm it, and submit the change themselves, even if they asked the user's dot to fix everything. - Keep passwords and authentication codes inside a protected manager or official provider flow. Never ask for them or a vault export in chat, or expose them in page inspection, screenshots, logs, or notes. Say "I can't see your passwords" only when the integration enforces that. The user's dot only needs account references and non-secret status.
- Reach the provider's genuine account settings independently of a warning email. Prepare its supported change or reset flow, show the user how to generate a unique password in their manager, and make sure they can recover it before they submit. Keep the last working session open. The user also handles any required sign-in, biometric, or multifactor step.
- After the user completes the change, follow
<confirmation_policy>for saving the specific credential in the chosen manager. If that save is already explicitly authorized and a protected tool can do it without exposing the secret, use it; otherwise ask immediately before saving or guide the user through it. Check the exact account and domain. If the provider accepted the change but the save failed, stop work on other accounts until this one can be recovered.
Show full SKILL.md (360 more words)Show less
Verify and finish
- Track changed, saved, and sign-in verified separately. Use provider or manager status where it is available and label anything reported only by the user. Where supported, guide a fresh sign-in without risking lockout; an already open session is not proof. Say which checks still need the user.
- Keep a minimal private checkpoint with account references, findings, authorization, results, and next steps; never include secrets. After an interruption or unclear response, inspect the current provider and manager status before suggesting another reset.
- Report how many distinct accounts were changed, saved, and verified, and what remains. If nothing was flagged, say which sources you checked. If there is evidence of stolen sessions or a compromised device, explain that a password change may leave that risk unresolved.
- Keep the completion message short. A little celebration is fine after the work is verified. Only add personal details supported by evidence, and stay within the requested cleanup.
Examples
- User: "Chrome says four passwords were exposed. Help me fix them and save the replacements in Chrome."
- dot: "I found four current warnings. I'll open each official reset page. You'll need to enter, confirm, and submit each new password. I'll keep track of what's changed and saved"
- dot: When the evidence supports it: "All four changes and Chrome saves are confirmed 🎉 Three fresh sign-ins worked but the fourth still needs you."
- User: "A breach alert says my email was leaked. Do I need to reset this password?"
- dot: "The alert names your email, but I haven't found evidence that your current password was exposed. I'll take a look at your password manager's current report before recommending a reset"
- User: "The site accepted my new password, but Chrome didn't save it. Can we do the next one?"
- dot: "Let's recover this account in Chrome first. Keep the site open and I'll guide you through the protected save. Then we'll continue."
- User: "Just do the last reset for me. I can send you the code."
- dot: "Don't share the code with me. I can open the official page and show you what to do, but you'll need to enter, confirm, and submit the new password yourself"
© asgeirtj, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in OpenAI/dots/skills/secure-me of asgeirtj/system_prompts_leaks.
Open the folder on GitHubat commit 60d44cc
Compare with similar skills
Secure Me next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Secure Me this skillasgeirtj/system_prompts_leaks | 69k | — | ~1.3k | Automated safety check: Pass | CC0-1.0 | |
| Password Field Securitythedaviddias/Front-End-Checklist | 74k | — | ~458 | Automated safety check: Pass | MIT | |
| Detecting Email Account Compromisemukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~823 | Automated safety check: Pass | Apache-2.0 | |
| Container Security Hardeningsickn33/agentic-awesome-skills | 47k | 1 repos | ~1k | Automated safety check: Notes | MIT | |
| Security and Hardeningaddyosmani/agent-skills | 104k | 1 repos | ~4.4k | Automated safety check: Notes | MIT | |
| Security Scanaffaan-m/ECC | 276k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Detecting Email Account Compromise
mukul975/Anthropic-Cybersecurity-Skills
Detect compromised O365 and Google Workspace email accounts by analyzing Unified Audit Logs and Azure AD sign-in logs for impossible travel, inbox rule creation/deletion (Set-InboxRule…
Container Security Hardening
sickn33/agentic-awesome-skills
Harden Docker/container images and runtime deployments with secure base images, non-root users, CVE scanning, SBOM/signing, seccomp/AppArmor, and Kubernetes pod security controls.
Security and Hardening
addyosmani/agent-skills
Applies a threat-model-first approach to web code that handles untrusted input, authentication, data storage, dependencies or personal data.
Security Scan
affaan-m/ECC
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield.
Quarkus Security
affaan-m/ECC
Quarkus security implementation patterns: JWT and OIDC authentication, @RolesAllowed RBAC and SecurityIdentity checks, Bean Validation and custom validators, parameterized Panache queries, BCrypt…
More from asgeirtj/system_prompts_leaks
All 128 skills in this repoFleet Manager for Agent Sessions
asgeirtj/system_prompts_leaks
Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.
Muse Code Product Doctor
asgeirtj/system_prompts_leaks
Diagnoses a Muse Code installation's own failures from binary and session evidence, instead of treating the report as an ordinary repository bug.
DOCX
asgeirtj/system_prompts_leaks
A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx).
Agents Project Coordinator
asgeirtj/system_prompts_leaks
Runs a goal as a project in which the agent coordinates separate agent threads, judging when to split the work, and interviews you first when nothing can be verified.
Muse Plugin Creator
asgeirtj/system_prompts_leaks
Creates and validates a new native Muse plugin package in the current workspace, limited to five capability families, and leaves installation to you.
Deep Research
asgeirtj/system_prompts_leaks
A skill your agent uses when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or…
Questions about Secure Me
What does Secure Me do?
Find compromised passwords in the user's personal accounts, prepare official reset flows, hand over before the user enters and submits each new credential, and help verify the change and authorized…. Secure Me is an agent skill from asgeirtj/system_prompts_leaks. Find compromised passwords in the user's personal accounts, prepare official reset flows, hand over before the user enters and submits each new credential, and help verify the change and authorized password-manager save.
How do I install Secure Me in Claude Code?
Run `npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a claude-code`. Or copy the skill folder (OpenAI/dots/skills/secure-me in asgeirtj/system_prompts_leaks) into .claude/skills/secure-me in your project. Claude Code loads it when a task matches its description.
How do I install Secure Me in Codex?
Run `npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a codex`. Or copy the skill folder (OpenAI/dots/skills/secure-me in asgeirtj/system_prompts_leaks) into .agents/skills/secure-me in your project. Codex loads it when a task matches its description.
Can I use Secure Me in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add asgeirtj/system_prompts_leaks --skill secure-me -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/secure-me, .gemini/skills/secure-me, .github/skills/secure-me and .opencode/skills/secure-me in your project.
What does Secure Me need to run?
SKILL.md names no scripts, command-line tools or credentials: Secure Me is instructions for the agent only.
Does Secure Me access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Secure Me safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Secure Me use?
Secure Me is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Secure Me use?
About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Secure Me?
Skills that share tags, products or a category with Secure Me: Password Field Security (thedaviddias/Front-End-Checklist, 74k stars), Detecting Email Account Compromise (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Container Security Hardening (sickn33/agentic-awesome-skills, 47k stars) and Security and Hardening (addyosmani/agent-skills, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Secure Me?
asgeirtj (a GitHub user) maintains it in asgeirtj/system_prompts_leaks, which has 69,280 GitHub stars. The repository holds 128 skills in this directory. The repository was last updated on October 10, 2026.
Source: asgeirtj/system_prompts_leaks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.