hetu-lyrics-blessing@1.0.2
CAUTION· install onlyPublisher 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.
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 scenariosStatic findings
result = 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.result = 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.subprocess.run('agent-browser close', shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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%- 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.
- 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.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.