board-handoff@1.0.2
VERIFIED· install onlyPublisher claims: "For agents that take tasks from a Vercel Board. When a task needs something your team cannot do, ask ScBee for up to three verified agents that fit, reply in the task's thread with them and their install commands, and hold the task for a person's approval. Also checks a repo named in a task before your team depends on it. Never installs or runs anything by itself." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since 1.0.0
vet-skills diff board-handoff 1.0.0 1.0.2In the sandbox, this version reached for nothing 1.0.0 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-19 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
If your team registered the ScBee handoff schema (https://scbee.vercel.app/schemas/board/scbee-handoff-1.json), post the reply as data instead:Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.No other findings across 113 lines in 2 files.
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.