Skills/ClawHub/lobster-market

lobster-market@2.1.0

CAUTION· install only

Publisher claims: "通过自然语言对话管理龙虾市场(Lobster Market)上的 AI Agent。用户可以用日常语言完成 Agent 注册、Skill 发布、服务发现与调用、钱包管理等全流程操作,无需记忆任何命令。 Manage AI Agents on Lobster Market via natural language...." Observed in sandbox: sends data to mindcore8.com.

Registry ClawHubPublisher xtaq · publishing for 266 daysInstalls 2,289Last detonated 7 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
7 of 7 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to mindcore8.com.

Behavior trace

Honeypot run · 16 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2snetworkCONNECT tcp://mindcore8.com:443 · not in the allow-list, refused
0.2snetworkCONNECT tcp://mindcore8.com:443 · not in the allow-list, refused
0.2snetworkCONNECT tcp://mindcore8.com:443 · not in the allow-list, refused
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: lobster.py: error: the following arguments are required: command
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: ❌ websockets not installed. Run: pip3 install websockets
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5snetworkCONNECT tcp://mindcore8.com:443 · not in the allow-list, refused
0.5sprocessexec /usr/bin/dirname
0.5sprocessexec /usr/bin/mkdir
0.5sprocessexec /usr/bin/curl
0.5sprocessexited 1:
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
16sprocessexited 1: ❌ aiohttp required. Run: pip3 install aiohttp
16sprocessbundled script run in the sandbox with no arguments · not named in the instructions
16sprocessexited 1: ❌ aiohttp required. Run: pip3 install aiohttp
16sprocess7 of 7 bundled scripts run with no arguments
16sprocessscript backend runs setup only
16sprocessscript backend runs setup only
16sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandscripts/start-agents.sh:166 · Process kill command — agent can terminate processes[ -n "$adapt_pid" ] && kill -0 "$adapt_pid" 2>/dev/null && adapt_status="▶ running ($adapt_pid)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/start-agents.sh:146 · Process kill command — agent can terminate processesif kill -0 "$pid" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/agent-launcher.py:140 · Python subprocess execution detectedproc = subprocess.Popen(cmd, stdout=lf, stderr=subprocess.STDOUT, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/start-agents.sh:147 · Process kill command — agent can terminate processeskill "$pid"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/agent-launcher.py:171 · Python subprocess execution detectedproc = subprocess.Popen(cmd, stdout=lf, stderr=subprocess.STDOUT, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/start-agents.sh:167 · Process kill command — agent can terminate processes[ -n "$conn_pid" ] && kill -0 "$conn_pid" 2>/dev/null && conn_status="▶ running ($conn_pid)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/start-agents.sh:126 · Process kill command — agent can terminate processesif ! kill -0 $(cat "$PID_DIR/$role-adapter.pid") 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,558 tok
1 file · 12 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.

What would make this Verified

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim xtaq: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim xtaqPropose a patch to the maintainer