Skills/Glama/fritzkit

fritzkit@0.1.0

CAUTION· install only

Publisher claims: "Enables agents to turn a JSON part specification into first-class Fritzing parts, with validation, rendering, export, and installation across breadboard, schematic, PCB, and icon views." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher pmaxhogan · publishing for 3 daysInstalls 0Last detonated 3d ago

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: Caution 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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso 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 under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- <the server's command>

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 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Text pushed off-screen by whitespace; README links to an external installer; Destructive file system command detected. 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

MEDIUM
Process kill commandsrc/mcp/server.ts:4 · Process kill command — agent can terminate processes* carrying the human message, never as an exception that would kill the server.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Text pushed off-screen by whitespaceskills/fritzkit/SKILL.md:675 · Text pushed off-screen by whitespace| a WARNING about gaps after removing pins is expected and harmless; never renumber `pinIds` to "fix" it |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
README links to an external installerexamples/xiao-esp32-c6/README.md → https://files.seeedstudio.com/wiki/XIAO-KiCad-Library/New_XIAO_Series_Footprints.ziphttps://files.seeedstudio.com/wiki/XIAO-KiCad-Library/New_XIAO_Series_Footprints.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskills/fritzkit/SKILL.md:15 · npx invocation of non-well-known package — may execute untrusted code| step | CLI (`npx fritzkit ...` or `fritzkit ...`) | MCP tool (server `fritzkit`) |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/core/kicad/index.ts:102 · File type combined with upload action — agent may exfiltrate local data files/** Convert a parsed footprint into a part.json fragment (PartSpecInput). */Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Destructive file system command detectedsrc/core/export/prune.ts:196 · Destructive file system command detected// Folders first; only ids whose folder is really gone leave the bin, so a failed rmFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionsrc/core/workspace.ts:9 · File type combined with upload action — agent may exfiltrate local data files* Only part.json and assets/ feed the compiler, so build output never changes a moduleId.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageskills/fritzkit/SKILL.md:3 · npx invocation of non-well-known package — may execute untrusted code… Parts. You do the research and vision work with your own tools; fritzkit (CLI `npx fritzkit` or the `fritzkit` MCP server) is offline and deterministic. --- # fritzkit: bu…Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionsrc/mcp/server.ts:440 · File type combined with upload action — agent may exfiltrate local data files{ description: "Return the part.json JSON Schema.", inputSchema: { workspace: ws } },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 actionsrc/server/api.ts:250 · File type combined with upload action — agent may exfiltrate local data files* Validate a part.json body for PUT. Returns the raw object to write (with connectorFix: 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
≈8,795 tok
1 file · 80 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.

What would make this Verified

7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim pmaxhogan: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pmaxhoganPropose a patch to the maintainer