school-song-maker@0.2.0
BLOCKED· install onlyPublisher claims: "Turn your school, class, motto, and memories into original lyrics and a sing-along class song, graduation song, or welcome song." Observed in sandbox: reads credential files, sends data to api.beatra.ai, api.beatra.cn.
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
What changed since 0.1.9
vet-skills diff school-song-maker 0.1.9 0.2.0This version reaches for something 0.1.9 did not: 2 new hosts (api.beatra.ai, api.beatra.cn) · 1 new credential file (~/.beatra/credentials.json). Compared from the two recorded runs, not from source.
- New hosts
- api.beatra.ai, api.beatra.cn
- New credential files
- ~/.beatra/credentials.json
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 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 api.beatra.ai, api.beatra.cn.
Behavior trace
Honeypot run · 1 s · 2 scenariosStatic findings
"command": f"npx skills update {slug} -p -y (run in {_shell_quote(str(directory))})",Fix: Pin versions and sources; vendor anything fetched at install time.return None if source is None else {"source": source, "command": f"npx skills update {slug} -g -y"}Fix: Pin versions and sources; vendor anything fetched at install time.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
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.
- 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.
- 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 beatra-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.