Skills/npm/zames_pro

zames_pro@2.96.24

CAUTION· not started

Publisher claims: "Terminal coding agent that drives a real browser to chat with DeepSeek, Qwen or GLM — no API key required. Reads and edits files, runs commands, commits to git, like Claude Code / Codex CLI." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher viqto0r · publishing for 57 daysInstalls 66,544Last detonated 4d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution 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 deepseek.com, z.ai, no-color.org, qwen.ai, duckduckgo.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
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. 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 -- npx -y zames_pro

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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-11 and scored it 77/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 4 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.1sprocessexited 1: Node.js v22.23.4
3.9sprocessdependency install exit 1 · npm error For a full report see: npm error /tmp/ks-detonate-owBJmK/task/home/.npm/_logs/2026-11-11T00_43_21_893Z-eresolve-report.txt npm error A complete log of this run can be found in: /tmp/ks-detonate-owBJmK/task/home/.npm/_logs/2026-11-11T00_43_21_893Z-debug-0.log
3.9sclaimednot started: dependency install failed (exit 1); the server itself was not observed
3.9sprocessscript backend runs setup only
4.0sprocesssecond launch, clock +45 days, CI unset
4.1sprocessexited 1: Node.js v22.23.4

Static findings

MEDIUM
npx invocation of non-well-known packagedist/i18n/config.js:365 · npx invocation of non-well-known package — may execute untrusted codeen: 'Check command (e.g. npx tsc --noEmit)',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsdist/permissions.js:207 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// `command` (`cat /etc/passwd`), not in a `path` key. Scanning the commandFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commanddist/browser.js:311 · Process kill command — agent can terminate processes// NOTE: we deliberately do NOT kill stray chrome processes here. Per theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/mcp.js:48 · npx invocation of non-well-known package — may execute untrusted code// `{command: "npx --user-data-dir=/tmp/x", args: ["@playwright/mcp"]}` isFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/agent-loop.js:1175 · File type combined with upload action — agent may exfiltrate local data filestranscript?.log('diagnostics', { tool: call.tool, output: diag });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/index.js:1989 · Process kill command — agent can terminate processes// A TUI mount failure must not kill the agent. We surface it and let theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/agent-loop.js:1163 · File type combined with upload action — agent may exfiltrate local data filestranscript?.log('hook_post_output', { tool: call.tool, output: post });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/agent-loop.js:1229 · Process kill command — agent can terminate processes// itself has finished (we cannot kill an arbitrary child process fromFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packagedist/diagnostics.js:4 · npx invocation of non-well-known package — may execute untrusted codecommand: 'npx tsc --noEmit',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/i18n/config.js:364 · npx invocation of non-well-known package — may execute untrusted coderu: 'Команда проверки (например, npx tsc --noEmit)',Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/shell.js:228 · Process kill command — agent can terminate processes// Own process group so a kill reaches children (a dev server spawns more).Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commanddist/shell.js:292 · Process kill command — agent can terminate processesreturn `Failed to kill ${id}: ${e.message}`;Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiondist/index.js:4384 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(theme.system(limitsEmptyMessage(sendLogPath(logsDir, config.provider), t)));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commanddist/fsutil.js:83 · File permission modification command — agent changes file ownership/permissions// Best-effort: on Windows chmod is largely a no-op and can throw.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commanddist/fsutil.js:12 · File permission modification command — agent changes file ownership/permissions// multi-user machine. We also chmod the target after rename because aFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commanddist/browser.js:400 · Process kill command — agent can terminate processes// Do NOT kill a foreign chrome (see AGENTS.md): only clear theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/index.js:393 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconst devMode = hasFlag('--dev') || config.hotReload === true;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/agent-loop.js:1085 · Process kill command — agent can terminate processes// Best-effort by design — hooks must not be able to kill the loop.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/agent-loop.js:1142 · Process kill command — agent can terminate processes// child-process kill is to check it periodically. 100ms is cheap andFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Auto-update or dynamic fetch configurationdist/index.js:391 · Auto-update or dynamic fetch configuration — agent may load new code at runtime// Enabled by the --dev flag (`npm run dev` sets it) or config.hotReload === true.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/compact.js:57 · File type combined with upload action — agent may exfiltrate local data filestranscript?.log('hook_pre_compact', { output: out });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/browser.js:312 · Process kill command — agent can terminate processes// project rules, an agent must never kill a browser it did not start —Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/agent-loop.js:109 · File type combined with upload action — agent may exfiltrate local data filestranscript?.log('hook_session_start', { output: out });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/index.js:1995 · File type combined with upload action — agent may exfiltrate local data files// All command output (console.log/error) must go ABOVE the input line,Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/context.js:186 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file/** MEMORY.md is append-only, so it gets its own (larger) budget. */Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commanddist/tools.js:478 · File permission modification command — agent changes file ownership/permissions'mkdir rmdir touch chmod chown').split(' '));Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/index.js:4131 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// `/remember <text>` — append a durable note to the project MEMORY.md.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/index.js:4134 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// write to the workdir's own MEMORY.md (the deepest file the loader reads)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commanddist/tools.js:477 · Process kill command — agent can terminate processes'insert remove drop restart stop start install kill move rename copy ' +Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/index.js:4173 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file'configs, CI, and a sample of source files). Then write AGENTS.md with: ' +Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/context.js:697 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// AGENTS.md is head-clipped; MEMORY.md is append-only so it uses theFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commanddist/subagent.js:111 · Process kill command — agent can terminate processes// browser, and leaving the nested (no-op) callbacks in place would killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/i18n/help.js:571 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction fileen: '/remember <text> append a note to the project MEMORY.md (creates it)',Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commanddist/statusline.js:37 · Process kill command — agent can terminate processes// Own process group so the timeout can kill the WHOLE tree. A commandFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/tools.js:283 · Process kill command — agent can terminate processes'run_in_background=true, and optionally kill it. id — the id returned ' +Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/tools.js:286 · Process kill command — agent can terminate processesfn: async ({ id, kill }) => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/index.js:4167 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// Like Codex: let the agent explore the project and write AGENTS.md viaFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈83 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for zames_pro@2.96.24 as of 4d ago. This is the package itself, not its dependencies.

What would make this Verified

3 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim viqto0r: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim viqto0rPropose a patch to the maintainer