waterloo-mcp@r1
VERIFIED· install onlyPublisher claims: "Enables read-only access to University of Waterloo accounts across LEARN, WaterlooWorks, Odyssey, Crowdmark, Outline, Piazza, and UW Flow, exposing courses, grades, assignments, announcements, jobs, exam schedules, assessments, outlines, posts, and course info through MCP tools. It also reports sign-in status without submitting, posting, or changing anything." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 13 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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
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
AUTHAUTH_CLIENT_IDAUTH_CLIENT_SECRETPIAZZA_PASSWORDUW_PASSWORDConfiguration, not credentials: ALLOWED_USERS, AUTOLOGIN, DATA_DIR, KEEPALIVE_MINUTES, MCP_TRANSPORT, PIAZZA_EMAIL, PUBLIC_URL, UW_USERNAME- Where it talks to
- uwaterloo.ca (its own)Also crowdmark.com, sharepoint.com, piazza.com, microsoftonline.com, uwflow.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 crowdmark.com, sharepoint.com, piazza.com, microsoftonline.com, uwflow.com as well as its own vendor. The guard injects AUTH, AUTH_CLIENT_ID, AUTH_CLIENT_SECRET, PIAZZA_PASSWORD, UW_PASSWORD only into requests to uwaterloo.ca (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is waterloo-mcp@r1 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 2026-11-18 and scored it 88/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
subprocess.run(["ssh", host, remote], input=state.encode(), check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.env_file: .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.&& mkdir /data && chown app /dataFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.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.