Skills/Glama/tabgeist

tabgeist@0.1.1

VERIFIED· install only

Publisher claims: "Enables any AI agent to work inside your own signed-in Chrome or Edge, with risky steps gated behind approvals the agent cannot skip, receipts for every action, routines that replay without the AI, and per-site packs that read a site's own data. Everything runs locally, so pages, cookies and passwords never leave your machine." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher muhammadawais-automation · publishing for 3 daysInstalls 0Last detonated 3d ago
$npx skills add tabgeist
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso evil.com, x.com, linkedin.com, whatsapp.com, evil.example, i.test, shop.test, a.test, x.invalid, google.com, example.org, other.org, bank.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Prompt injectionextension/README.md:11 · Prompt injection — known jailbreak technique reference · informational: not an instruction file1. Turn on **Developer mode** (top right on `chrome://extensions`, left side on `edge://extensions`).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageextension/README.md:11 · Authorization escalation language · informational: not an instruction file1. Turn on **Developer mode** (top right on `chrome://extensions`, left side on `edge://extensions`).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageREADME.md:56 · Authorization escalation language · informational: not an instruction file1. Turn on **Developer mode** → **Load unpacked** → paste the folder.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Hidden zero-width characters detectedsrc/engine/read.test.ts:19 · Hidden zero-width characters detected — may conceal contentexpect(cleanText('Ali\n\n\n\n Han bro \n​\nYou: hello ')).toBe('Ali\n\nHan bro\n\nYou: hello')Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
LOW
Prompt injectionREADME.md:56 · Prompt injection — known jailbreak technique reference · informational: not an instruction file1. Turn on **Developer mode** → **Load unpacked** → paste the folder.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Hidden zero-width characters detectedsrc/engine/read.ts:83 · Hidden zero-width characters detected — may conceal content.replace(/[​-‍⁠‪-‮⁦-⁩]/g, '')Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File type combined with upload actionsrc/routines/runner.ts:259 · File type combined with upload action — agent may exfiltrate local data filesconst run = async (q: ActRequest) => { const [rec, log] = await withNetGate(t, gate, () => actOnPage(t, q, opts)); wouldSend.push(...log.wouldSend); return rec }Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
AWS access key pattern detectedsrc/safety/safety.test.ts:21 · AWS access key pattern detected — possible hardcoded or harvested keyexpect(kinds('AKIAABCDEFGHIJKLMNOP')).toEqual(['api key'])Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Bidirectional text override characters detectedsrc/engine/read.ts:83 · Bidirectional text override characters detected — may hide content direction.replace(/[​-‍⁠‪-‮⁦-⁩]/g, '')Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07

Cost to the agent

Instructions loaded
≈2,124 tok
2 files · 80 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.