Skills/npm/humantype

humantype@0.1.0

VERIFIED· install only

Publisher claims: "Human-like typing for AI browser agents: keystroke plans with uneven timing, thinking pauses, typos fixed with Backspace and code identifiers pasted from the clipboard, rendered for Claude in Chrome and Browser MCP." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher w21180239 · publishing for 7 daysInstalls 355Last detonated 23 min ago
$claude mcp add humantype -- npx -y humantype
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script run with no arguments, with decoy credentials in the environment · 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 84/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocess1 of 1 bundled script run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsplugins/human-typing/skills/human-typing/scripts/humantype.mjs:86 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespackage.json package-lock.json tsconfig.json jsconfig.json readme.md readme dockerfile makefile .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionplugins/human-typing/skills/human-typing/SKILL.md:50 · File type combined with upload action — agent may exfiltrate local data files6. For N = 0 .. batches-1, run `H batch S/plan.json N` and send the printed output unchanged as one call:Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionplugins/human-typing/skills/human-typing/SKILL.md:53 · File type combined with upload action — agent may exfiltrate local data files…If step 4 ran: `H clip restore`, also when a batch failed. Then `H verify S/plan.json` and send its output: Chrome as the input of `mcp__claude-in-chrome__javascript_tool`, Browser MCP as the `commands` of `…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,078 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

Not checked against OSV yet; the weekly check has not reached this version.