widehive@1.4.0
VERIFIED· install onlyPublisher claims: "WideHive — Wide Research orchestration for AutoClaw / OpenClaw agents: fan out 100+ context-isolated sub-agents over a large target list, merge programmatically with zero LLM calls, synthesize scenario-shaped reports (financial tables / academic reviews / tech matrices). Triggers: widehive, wide research, batch research, 批量调研, 大范围调研." 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
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 2026-11-07 and scored it 91/100 (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
- `merged.csv` / `merged.json` — programmatic merge outputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.- `plan.json` — scenario, field template, batch_size, max_output_words, max_retries, output_form; watch runs add `mode` and a `watch` block (see Watch mode)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.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.