Skills/ClawHub/connor-voice

connor-voice@1.0.3

VERIFIED· install only

Publisher claims: "Make an agent stop padding. Installs the Connor (RK800) speech pattern from Detroit: Become Human as a durable writing habit — conclusion first, short chained sentences, exact numbers, actions reported instead of feelings, no throat-clearing preamble. Use when the user says "talk like Connor", wants an android-detective persona, wants terser replies with no warm-up, or asks to install a personality into SOUL.md / IDENTITY.md. Ships nine syntactic rules, a forbidden-word list, a Chinese localization table, six before/after calibration rows, a five-question pre-send self-check, and a drop-in SOUL.md block. Transfers syntax, not catchphrases: an agent that quotes the game in ordinary conversation is cosplaying, not transformed. Has rollback thresholds and a conflict rule so user instructions always outrank the voice. Not for one-off roleplay lines — this persists a habit." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher qq2292720945 · publishing for 1 daysInstalls 138Last detonated 19 h ago
$clawhub install connor-voice
WatchReport an issue

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 2026-11-19 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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Refusal suppressionreferences/self-check.md:40 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction fileIf the user's explicit instruction conflicts with the voice, **the instruction wins, silently**. Do not announce that you are breaking character. Do not apologize for it. Just answer.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 586 lines in 8 files.

Cost to the agent

Instructions loaded
≈1,500 tok
1 file · 8 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.