Adversarial probe of a site's authentication. Drives the login flow once, records the trajectory, then runs a configurable set of probes against the captured artifacts and live page. Output is a structured findings.md inside the RVF container.
When to use
Pre-deployment audit of a new auth flow.
Investigating a suspected token leak or redirect issue.
Establishing a baseline for ongoing regression checks.
Steps
Open a recorded session via browser-record.
Drive the auth flow as in browser-login (credentials come from --credentials <handle> referencing browser-cookies if the run is a re-auth probe).
Run probes:
csrf: inspect the login POST in the trajectory; verify a same-origin token field is present and non-empty.
redirect: watch browser_get-url after each nav for cross-origin redirects with auth state in the URL or fragment. Flag any token-bearing URL that crosses an origin boundary.
cookie: walk document.cookie via browser_eval. For each cookie, check Secure, HttpOnly, SameSite, expiry, and entropy of the value. Flag missing flags or short tokens. Pass each through aidefence_scan to flag PII embedded in cookie values.
oauth: if the flow involves a third-party provider, capture the authorization request, verify state and nonce are present and high-entropy, verify redirect_uri matches the registered callback domain.
Quarantine any token / credential / PII captured during probing — it stays inside the RVF container's findings, never returns to the model unredacted (aidefence_is_safe gate from browser-extract applies if you read the findings back).
Write findings.md with one section per probe, severity rating per finding, and a verdict (pass / warn / fail).
Index the session in browser-sessions with tag: auth-probe so future audits compare against it.
Caveats
This skill probes; it does not exploit. Do not chain follow-up requests using a captured token.
Credentials must come from a vaulted handle or interactive entry. Never hardcode them in the field map.
Some probes require multiple page loads. Trajectory step count for an auth probe typically lands at 15–40 steps; budget accordingly.
The output is structured for human review. Do not auto-act on findings without surfacing them to the user first.
1---2name: browser-auth-flow3description: Browser Auth Flow4---56# Browser Auth Flow
78Adversarial probe of a site's authentication. Drives the login flow once, records the trajectory, then runs a configurable set of probes against the captured artifacts and live page. Output is a structured `findings.md` inside the RVF container.
910## When to use
1112- Pre-deployment audit of a new auth flow.
13- Investigating a suspected token leak or redirect issue.
14- Establishing a baseline for ongoing regression checks.
1516## Steps
17181. **Open a recorded session** via `browser-record`.
192. **Drive the auth flow** as in `browser-login` (credentials come from `--credentials <handle>` referencing `browser-cookies` if the run is a re-auth probe).
203. **Run probes**:
2122 - **`csrf`**: inspect the login POST in the trajectory; verify a same-origin token field is present and non-empty.
23 - **`redirect`**: watch `browser_get-url` after each nav for cross-origin redirects with auth state in the URL or fragment. Flag any token-bearing URL that crosses an origin boundary.
24 - **`cookie`**: walk `document.cookie` via `browser_eval`. For each cookie, check `Secure`, `HttpOnly`, `SameSite`, expiry, and entropy of the value. Flag missing flags or short tokens. Pass each through `aidefence_scan` to flag PII embedded in cookie values.
25 - **`oauth`**: if the flow involves a third-party provider, capture the authorization request, verify `state` and `nonce` are present and high-entropy, verify `redirect_uri` matches the registered callback domain.
26274. **Quarantine** any token / credential / PII captured during probing — it stays inside the RVF container's findings, never returns to the model unredacted (`aidefence_is_safe` gate from `browser-extract` applies if you read the findings back).
285. **Write `findings.md`** with one section per probe, severity rating per finding, and a `verdict` (pass / warn / fail).
296. **Index** the session in `browser-sessions` with `tag: auth-probe` so future audits compare against it.
3031## Caveats
3233- This skill probes; it does not exploit. Do not chain follow-up requests using a captured token.
34- Credentials must come from a vaulted handle or interactive entry. Never hardcode them in the field map.
35- Some probes require multiple page loads. Trajectory step count for an auth probe typically lands at 15–40 steps; budget accordingly.
36- The output is structured for human review. Do not auto-act on findings without surfacing them to the user first.
Run npx skillmds@latest add gabrielmoreira/browser-auth-flow in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Browser Auth Flow It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.