udesa-mcp@0.1.1
CAUTION· install onlyPublisher claims: "Enables an AI agent to access a Moodle Campus Virtual account with the user's own credentials, reading course content, files, forums, notices, calendar, grades and quiz attempts for every enrolled course. Teachers, managers and course creators also get access to other participants' data and to planned, verified write operations such as forums, grading, attendance, quizzes, groups, content and H5P activities." 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
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 cafecito.app, claude.ai, claude.com, chatgpt.com, microsoft.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.
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 2026-11-13 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Auto-update or dynamic fetch configuration; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
// ADR-117: herramienta LTI 1.3 del laboratorio en el curso. Todo fijo salvo el nombre: URLs delFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.import type { RemoteConfig } from "./config.js";Fix: Pin versions and sources; vendor anything fetched at install time.async function approve(cfg: RemoteConfig, signer: TokenSigner, form: URLSearchParams): Promise<Response> {Fix: Pin versions and sources; vendor anything fetched at install time.export function readRemoteConfig(env: Record<string, string | undefined> = process.env): RemoteConfigResult {Fix: Pin versions and sources; vendor anything fetched at install time.async function approvalPage(cfg: RemoteConfig, signer: TokenSigner, write: WriteApp, planId: string, req: Request, logger: Logger): Promise<Response> {Fix: Pin versions and sources; vendor anything fetched at install time.import { readRemoteConfig, type RemoteConfig } from "./config.js";Fix: Pin versions and sources; vendor anything fetched at install time.export type RemoteConfigResult = { ok: true; config: RemoteConfig } | { ok: false; missing: string[] };Fix: Pin versions and sources; vendor anything fetched at install time.const s = text.replace(/^/, "");Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…INTERNAL"; throw e; } finally { this.opts.logger.log(outcome === "ok" ? "info" : "warn", "moodle_write_call", { correlation_id: correlationId, wsfunction: "webservice/upload.php", outcome, files: files.length, duration_ms: Date.now() - sta…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.const text = new TextDecoder("utf-8", { fatal: true }).decode(bytes).replace(/^/, "");Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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.
What would make this Verified
4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim changazo: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.