Skills/npm/mcp

mcp@5.23.7

VERIFIED· install only

Publisher claims: "MCP server for lousy-agents - provides AI coding assistant tools via the Model Context Protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher lousy-agents · publishing for 250 daysInstalls 10,016Last detonated 3d ago
$claude mcp add mcp -- npx -y @lousy-agents/mcp
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

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
GIGET_AUTHConfiguration, not credentials: __FAKE_FS_O_FILENAME__, __FAKE_PLATFORM__, CHOKIDAR_INTERVAL, CHOKIDAR_USEPOLLING, GIGET_GIT_HOST, GIGET_GITHUB_URL, GIGET_GITLAB_URL, GIGET_REGISTRY, TERM_PROGRAM, TERMINAL_EMULATOR, TERMINUS_SUBLIME, TESTING_TAR_FAKE_PLATFORM, WT_SESSION
Where it talks to
no vendor host named in the codeAlso sr.ht, bitbucket.com, githubusercontent.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names sr.ht, bitbucket.com, githubusercontent.com as well as its own vendor. The guard injects GIGET_AUTH only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @lousy-agents/mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

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 2026-11-11 and scored it 81/100 (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

HIGH
Hidden zero-width characters detecteddist/772.js:17 · Hidden zero-width characters detected — may conceal content…tring`&&(e>=`a`&&e<=`z`||e>=`A`&&e<=`Z`||e>=`0`&&e<=`9`||e===`$`||e===`_`||e===`‌`||e===`‍`||r.ID_Continue.test(e))},isDigit(e){return typeof e==`string`&&/[0-9]…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Unicode escape sequence detecteddist/913.js:28 · Unicode escape sequence detected — may contain obfuscated payloads…556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File permission modification commandpackage.json:36 · File permission modification command — agent changes file ownership/permissions"build": "rspack build --config rspack.config.ts && chmod +x dist/mcp-server.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commanddist/316.js:610 · File permission modification command — agent changes file ownership/permissionsreturn t.chmod === void 0 && t.noChmod === !1 && (t.chmod = !0), delete t.noChmod, t;Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commanddist/316.js:2507 · File permission modification command — agent changes file ownership/permissions…|| process.cwd())), this.strip = Number(e.strip) || 0, this.processUmask = this.chmod ? typeof e.processUmask == `number` ? e.processUmask : Ji() : 0, this.umask = ty…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Unicode escape sequence detecteddist/116.js:174 · Unicode escape sequence detected — may contain obfuscated payloads…=n;}return D};})(P$1);var X=P$1.exports;const DD=O(X);var uD=function(){return /\uD83C\uDFF4\uDB40\uDC67\uDB40\uDC62(?:\uDB40\uDC77\uDB40\uDC6C\uDB40\uDC73|\uDB40\uDC73\uDB40\uDC63\uDB40\uDC74|\uD…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Hidden zero-width characters detecteddist/913.js:28 · Hidden zero-width characters detected — may conceal content…tring`&&(e>=`a`&&e<=`z`||e>=`A`&&e<=`Z`||e>=`0`&&e<=`9`||e===`$`||e===`_`||e===`‌`||e===`‍`||r.ID_Continue.test(e))},isDigit(e){return typeof e==`string`&&/[0-9]…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Unicode escape sequence detecteddist/772.js:17 · Unicode escape sequence detected — may contain obfuscated payloads…556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F2\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actiondist/48.js:33 · File type combined with upload action — agent may exfiltrate local data files…hema=t.schema||Qe,this.onWarning=t.onWarning||null,this.legacy=t.legacy||!1,this.json=t.json||!1,this.listener=t.listener||null,this.implicitTypes=this.schema.compiledImplicit,this.typeMap=this.schema.compiledTypeMap,this.length=e.length,t…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 actiondist/873.js:28 · File type combined with upload action — agent may exfiltrate local data files…on Lt(e,t,n,r,i){if(e.position=t.keyPosition,t.keyIsMerge){It(e,t,r,i);return}!e.json&&t.tag.has(t.value,n)&&!t.overridable?.has(n)&&E(e,`duplicated mapping key`);let a=t.tag.addPair(t.value,n,r);a&&E(e,a),t.overridable?.delete(n)}function…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 detecteddist/913.js:31 · Hidden zero-width characters detected — may conceal content…;break}h+=e,m=`identifierName`},identifierName(){switch(v){case`$`:case`_`:case`‌`:case`‍`:h+=x();return;case`\\`:x(),m=`identifierNameEscape`;return}if(r.isIdCo…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File permission modification commanddist/316.js:2730 · File permission modification command — agent changes file ownership/permissionslet n = this.chmod && e.mode && (i.mode & 4095) !== e.mode, a = (t) => this[Q](t ?? null, e, r);Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Hidden zero-width characters detecteddist/772.js:20 · Hidden zero-width characters detected — may conceal content…ow N()}h+=e,m=`identifierName`},identifierName(){switch(v){case`$`:case`_`:case`‌`:case`‍`:h+=x();return;case`\\`:x(),m=`identifierNameEscape`;return}if(r.isIdCo…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File type combined with upload actiondist/653.js:894 · File type combined with upload action — agent may exfiltrate local data filesif (input.endsWith(".json")) return await _httpJSON(input, options);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commanddist/316.js:2502 · File permission modification command — agent changes file ownership/permissions}, super(e), this.transform = e.transform, this.chmod = !!e.chmod, typeof e.uid == `number` || typeof e.gid == `number`) {Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Hidden zero-width characters detecteddist/772.js:18 · Hidden zero-width characters detected — may conceal content`?(c++,l=0):e?l+=e.length:l++,e&&(s+=e.length),e}let S={default(){switch(v){case` `:case`\v`:case`\f`:case` `:case`\xA0`:case``:case`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Hidden zero-width characters detecteddist/913.js:29 · Hidden zero-width characters detected — may conceal content`?(c++,l=0):e?l+=e.length:l++,e&&(s+=e.length),e}let S={default(){switch(v){case` `:case`\v`:case`\f`:case` `:case`\xA0`:case``:case`Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07

Cost to the agent

Instructions loaded
≈59 tok
1 file · 15 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for @lousy-agents/mcp@5.23.7 as of 3d ago. This is the package itself, not its dependencies.