voice-setup@0.5.0
VERIFIED· install onlyPublisher claims: "Build, measure, edit, or switch a personal writing voice profile for the rabbit-writes plugin. Three ways in, from writing samples, from an interview, or from both together, which is the one to recommend. Use when the user wants to teach the system how they write, create their own writing style, set up or replace a voice, capture their tone, analyze documents they wrote to extract a voice, be interviewed about their style, change whose voice is active, blend two voices, or convert their writing samples into a reusable style profile. Also use when a draft "doesn't sound like me" and the saved profile needs correcting." 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 2026-11-08 and scored it 86/100 (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
"rx": "(?i)\\b(battle ?rhythm|kill chain|in the trenches|war ?room|weaponi[sz]e[ds]?|force multiplier|troops on the ground|boots on the ground)",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.run(argv, input=text.encode("utf-8"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.A suffix is stripped and `.rules.json` put back, so a name, a rules path,Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."rx": "(?i)\\b(war ?room|kill chain|in the trenches)",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.~/.claude/settings.json hooks, and `outputStyle`Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.proc = subprocess.run(argv, stdout=subprocess.PIPE,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.refuses chmod still gets the write, which is the point. Two callers doingFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."partial": "the vocabulary tiers drop the words carrying real technical meaning, from lexicon.json's technical_exempt. Not an allowance, which would let a second `delve` through; a named exemption lisFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.# non-ASCII anchor, `(#%E5%AD%97%E5%B9%95)`, is not a URL by URL_RX and survivesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.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.