AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Login Flow

skill-bettyguo-browser-skills-login-flow · by bettyguo

Signs into a site using credentials provided via `vars` (typically sourced from environment variables) or via a pre-saved Playwright persistent context. Never harvests or stores credentials. See docs/ethics.md.

No reviews yet
0 installs
13 views
0.0% view→install

Install

$ agentstack add skill-bettyguo-browser-skills-login-flow

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-bettyguo-browser-skills-login-flow)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Login Flow? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Login Flow

When to invoke

The user task requires authentication. The agent provides credentials in:

  • vars.username (or vars.email)
  • vars.password

Per and [docs/ethics.md](../../docs/ethics.md): we use the agent-provided creds only — typically sourced by the agent from env vars ($SITE_X_USER, $SITE_X_PASS) the user has set, or from a password manager the user controls. We never harvest, prompt for, or store credentials. The sensitive: true metadata flag tells the trace recorder to redact form-fill events in the exported zip.

Recipe

  1. waitfordom_ready timeout=5s
  2. waitforselector selector="input[type='password']" state=visible timeout=5s
  3. fill selector="input[type='email'], input[name='username'], input[name='email'], input[id='username'], input[id='email']" value="$vars.username"
  4. fill selector="input[type='password']" value="$vars.password"
  5. click selector="button[type='submit'], button:has-text('Sign in'), button:has-text('Log in'), input[type='submit']"
  6. wait extra=1000ms

Success criteria

  • assert novisibleelement selector="input[type='password']"
  • assert urlchangedsince=step1 OR cookiesetnamed="session"

When NOT to use

  • OAuth / SSO flows that redirect through identity providers

(Google, Microsoft, Okta). Use handle-oauth-redirect (v0.2.0).

  • Magic-link / passwordless flows. Out of v1 scope; agent must

poll its inbox separately.

  • MFA-protected logins. If MFA is enabled and there's no pre-saved

session, the recipe will hit the MFA challenge and stop. The agent surfaces the MFA prompt and asks the user how to proceed.

Known failures

  • **Sites that hide the password field until the email is submitted

first** (Google-style): the recipe fills email, submits, then needs to re-find the password field. v0.1 fails on these; the agent can retry with a "submit, wait, re-invoke" loop.

  • Captcha after a few failed attempts: detect-captcha should be

chained after this skill.

  • "Are you sure?" dialogs post-login: handle-modal-dialog chains.

Trace handling

Per sensitive: true:

  • form-fill events for password fields are recorded as `{value:

"[REDACTED]"}` in the trace

  • screenshots taken during this skill's steps are blackened over the

password field's bounding box (v0.1 omits screenshots from this skill entirely)

Related skills

  • dismiss-cookie-banner — sites with consent walls hit this first
  • detect-captcha — failed-login rate-limiting often triggers captcha

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.