Skills/ClawHub/research-first

research-first@0.1.0

VERIFIED

Publisher claims: "Do research with stopping criteria instead of vibes — five machine-checkable criteria (S1–S5) for when to stop, six breadth axes, nine associative-expansion directions (D1–D9), a journal template, and two CLI checkers that machine-verify a research journal and flag false confidence. Use when you are about to write a spec, design doc, or prompt that depends on facts you have not verified; when asked to research/investigate/look something up before starting; when reviewing whether an existing conclusion has traceable sources; or when you catch yourself citing a single secondary summary as if it were first-hand." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher catsmansion · joined 4 days agoInstalls 58Last detonated 42 h ago
$clawhub install research-first
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-01 and scored it 88/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

MEDIUM
Python subprocess execution detectedscripts/run_all.py:22 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

No other findings across 1,202 lines in 9 files.