Skills/ClawHub/hetu-lyrics-blessing

hetu-lyrics-blessing@1.0.2

CAUTION· install only

Publisher claims: "A daily lyrics blessing skill that sends a random Hetu (河图) song lyric to a designated recipient every day at 23:00. Lyrics are fetched from Baidu Baike usin..." Observed in sandbox: sends data to 43.163.178.99, 43.163.178.2, 240d:c040:1:40::53, 240d:c040:0:40::23.

Registry ClawHubPublisher trae1oung · publishing for 262 daysInstalls 1,255Last detonated 58 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script 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 68/100 (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 43.163.178.99, 43.163.178.2, 240d:c040:1:40::53, 240d:c040:0:40::23.

Behavior trace

Honeypot run · 5 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
4.7snetworkdirect connection to 43.163.178.99:465 (×2), bypassing the egress proxy · undeclared
4.7snetworkdirect connection to 43.163.178.2:465, bypassing the egress proxy · undeclared
4.7snetworkdirect connection to 240d:c040:1:40::53:465, bypassing the egress proxy · undeclared
4.7snetworkdirect connection to 240d:c040:0:40::23:465, bypassing the egress proxy · undeclared
4.7sprocess1 of 1 bundled script run with no arguments
4.7sprocessscript backend runs setup only
4.7sprocessscript backend runs setup only
4.7sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/send_lyrics.py:62 · Python subprocess execution detectedresult = subprocess.run(cmd, shell=True, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/send_lyrics.py:71 · Python subprocess execution detectedresult = subprocess.run(cmd, shell=True, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/send_lyrics.py:87 · Python subprocess execution detectedsubprocess.run('agent-browser close', shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈432 tok
1 file · 3 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

12 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 trae1oung: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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 trae1oungPropose a patch to the maintainer