Skills/ClawHub/humanize-text-skill

humanize-text-skill@0.1.1

VERIFIED· install only

Publisher claims: "Audit and rewrite Chinese or English content to remove AI tone, then pull it toward a target human voice. Use this skill when asked to remove AI tone, sound human, rewrite naturally, make a draft feel less templated, or match a target voice. Supports detect-only and edit-in-place modes, scene packs," Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher fendouai · publishing for 134 daysInstalls 760Last detonated 4d ago
$clawhub install humanize-text-skill
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 2026-11-10 and scored it 82/100 (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

CRITICAL
HTML comment carrying imperative instructions to the agentevals/run-eval.md:1 · HTML comment carrying imperative instructions to the agentMigrated from shuorenhua/evals/run-eval.md. SF/SNF cases validate the bilingual subtraction engine.Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
MEDIUM
File type combined with upload actiondetector/__tests__/readme-examples.test.js:96 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('\nREADME example numbers match engine output.');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Hidden zero-width characters detecteddetector/core/normalize.js:29 · Hidden zero-width characters detected — may conceal contentout = out.replace(/[​-‍⁠]/g, () => { flags.zeroWidth++; return ''; });Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07

Cost to the agent

Instructions loaded
≈4,450 tok
3 files · 96 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.