Skills/ClawHub/music-discovery-app

music-discovery-app@1.0.0

BLOCKED· install only

Publisher claims: "一个完全免费的音乐发现应用,集成多个免费音乐API,无需任何认证。提供音乐搜索、歌词显示、网络电台、演唱会信息等功能。" Observed in sandbox: reads credential files, sends data to telemetry.nextjs.org.

Registry ClawHubPublisher fish1981bimmer · publishing for 197 daysInstalls 814Last detonated 30 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 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 2026-11-22 and scored it 30/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Summary: reads credential files, sends data to telemetry.nextjs.org.

Behavior trace

Honeypot run · 15 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
15sfilesystemread ~/.npmrc
15sfilesystemread ~/.npm/_logs · ~/.npm/_cacache/index-v5/44/67/8042e8b78593a42df486c68bd5d1b5e5e4e25f58dbd7938f704d41915b83 · ~/.npm/_cacache/index-v5/a8/82/da13e7622a7c537487b3c2bdfbd393f9719a13691f4685cedb94cb3d7497 · ~/.npm/_cacache/index-v5/81/e7/d9e3a621cd85ad2be67c143bfc4a0ed59a7385d7b846687982bdd9628705 · ~/.npm/_cacache/content-v2/sha512/19/d7/c3ede58e5dc526dd01c2cc159e0ae741b45a078d45f5f5ac7746b9d41048a7e8bfc9bf1b5dc3f81f37023fe2a259cde1ceb9f414ad7800ce5ea4ada381f9 · ~/.npm/_cacache/index-v5/dd/98/9416c5c997b420dc78c6694ec378efa0b1a02ff5b14d0de06dd9bca00c1e outside project
15sfilesystemwrote ~/.npm/_cacache/tmp/ccc9621c · ~/.npm/_cacache/index-v5/44/67/8042e8b78593a42df486c68bd5d1b5e5e4e25f58dbd7938f704d41915b83 · ~/.npm/_cacache/tmp/7f0a528a · ~/.npm/_cacache/index-v5/a8/82/da13e7622a7c537487b3c2bdfbd393f9719a13691f4685cedb94cb3d7497 · ~/.npm/_cacache/tmp/f07efc87 · ~/.npm/_cacache/index-v5/81/e7/d9e3a621cd85ad2be67c143bfc4a0ed59a7385d7b846687982bdd9628705
15snetworkCONNECT tcp://registry.npmjs.org:443
15snetworkCONNECT tcp://telemetry.nextjs.org:443 · not in the allow-list, refused
15snetworkCONNECT tcp://telemetry.nextjs.org:443 · not in the allow-list, refused
15snetworkCONNECT tcp://telemetry.nextjs.org:443 · not in the allow-list, refused
15snetworkCONNECT tcp://telemetry.nextjs.org:443 · not in the allow-list, refused
15snetworkCONNECT tcp://telemetry.nextjs.org:443 · not in the allow-list, refused
15snetworkCONNECT tcp://telemetry.nextjs.org:443 · not in the allow-list, refused
15sprocessexec /usr/local/bin/npm
15sprocessexec /app/apps/web/node_modules/.bin/next
15sprocessexec /usr/bin/sed
15sprocessexec /usr/bin/dirname
15sprocessexec /usr/bin/uname
15sprocessexec /usr/bin/git
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sprocessexited 1: ModuleNotFoundError: No module named 'fastapi'
15sprocessbundled script run in the sandbox with no arguments
15sprocessexited 1: ModuleNotFoundError: No module named 'fastapi'
15sprocess3 of 3 bundled scripts run with no arguments
15sprocessscript backend runs setup only
15sprocessscript backend runs setup only
15sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandstart.sh:60 · Process kill command — agent can terminate processestrap "echo '停止服务...'; kill $BACKEND_PID $FRONTEND_PID; exit" INT TERMFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

No other findings across 8,860 lines in 28 files.

Cost to the agent

Instructions loaded
≈736 tok
1 file · 28 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

50 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%

An override rule (credential_read_plus_egress) caps this verdict regardless of the score. The first item below has to go before anything else counts.

  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs.
  2. 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.
  3. Unclaimed publisher≈ +8 on the totalClaim fish1981bimmer: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim fish1981bimmerPropose a patch to the maintainer