Skills/ClawHub/bilei-team

bilei-team@1.0.11

CAUTION· install only

Publisher claims: "避雷.skill 的多Agent重型版:四角色协作(反投毒取证官/定量对比官/主裁决官/价格情报官),角色隔离封死确认偏误。只认公关不了的数据——行政处罚、抽检不合格、召回公告,反软广反GEO投毒,逐款做信源利益审计(谁付的钱、能取事实层还是评价层),四问对价定量裁决(省多少现金、担什么风险、临界故障率p*、溢价ROI),预算S/A/B/C分级,结论先行给唯一推荐,适合>¥2000大件与安全关键品类。触发词:避雷选品团、选品、买什么、求推荐、对比、值不值得买、避坑、扫雷、性价比、质价比、溢价、历史低价、好价、预算XX买什么。" Observed in sandbox: sends data to cdn.jsdelivr.net.

Registry ClawHubPublisher zhashushu · publishing for 11 daysInstalls 226Last detonated 24 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
4 of 4 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

What changed since 1.0.10

vet-skills diff bilei-team 1.0.10 1.0.11

In the sandbox, this version reached for nothing 1.0.10 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-20 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Latin word with Cyrillic or Greek look-alike letters (homoglyph); Latin word with Cyrillic or Greek look-alike letters (homoglyph). Summary: sends data to cdn.jsdelivr.net.

Behavior trace

Honeypot run · 0 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sfilesystemread ~/.cache/bilei-team/update-check.json outside project
0.1snetworkCONNECT tcp://raw.githubusercontent.com:443 · not in the allow-list, refused
0.1snetworkCONNECT tcp://cdn.jsdelivr.net:443 · not in the allow-list, refused
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: premium_decision.py: error: the following arguments are required: cmd
0.3sprocess4 of 4 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)SKILL.md:296 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)ΔEACFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/manmanbuy_price.py:43 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)references/agent3_verdict.md:87 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)ΔEACFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈4,760 tok
1 file · 19 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

21 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 zhashushu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  4. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. 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 zhashushuPropose a patch to the maintainer