Skills/PyPI/tripitaka-mcp

tripitaka-mcp@1.1.0

CAUTION· not started

Publisher claims: "Local MCP server for the Pāli Tipiṭaka — verifiable Buddhist canon access for AI assistants, offline via SQLite" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher dhamma-seeker · publishing for 73 daysInstalls 98Last detonated 1 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
DATABASE_URLConfiguration, not credentials: EMBEDDING_DIMENSIONS, EMBEDDING_MODEL, MCP_HOST, MCP_PORT, MCP_TRANSPORT, TRIPITAKA_BACKEND, TRIPITAKA_DB_PATH, TRIPITAKA_ENABLED_LANGUAGES, TRIPITAKA_MCP_APP, TRIPITAKA_READER_BASE, TRIPITAKA_SKIP_MIGRATIONS
Where it talks to
tripitaka-mcp.com (its own)Also huggingface.co, watnyanaves.net, 84000.org, suttacentral.net, palitextsociety.org, palikanon.com, bhantedhammika.net — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names huggingface.co, watnyanaves.net, 84000.org, suttacentral.net, palitextsociety.org, palikanon.com, bhantedhammika.net as well as its own vendor. The guard injects DATABASE_URL only into requests to tripitaka-mcp.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets DATABASE_URL=tripitaka-mcp.com -- uvx tripitaka-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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-20 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Base64 encoding combined with network call; Hidden zero-width characters detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionmain.py:872 · File type combined with upload action — agent may exfiltrate local data filesscripts/setup_unaccent.sql (run post-data-load; deploy.sh does this).Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsdb/connection.py:39 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Copy .env.example to .env and set a secure password."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Base64 encoding combined with network callmcp_app_viewer_html.py:125 · Base64 encoding combined with network call — potential data exfiltration…i.credentials="same-origin",i}function o(e){if(e.ep)return;e.ep=!0;const i=r(e);fetch(e.href,i)}})();const pm="modulepreload",fm=function(t,n){return new URL(t,n).href},Ka={},gm=function(n,r,o){let e=Promise.resolve();if(r&&r.length>0){let…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 actionmcp_app_viewer_html.py:227 · File type combined with upload action — agent may exfiltrate local data files…tions=o,o.allowUnsafeEval||W({jitless:!0}),this.setRequestHandler(Jr,e=>(console.log("Received ping:",e.params),{})),this.setEventHandler("hostcontextchanged",void 0)}registerCapabilities(n){if(this.transport)throw Error("Cannot register c…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 detectedmcp_app_viewer_html.py:187 · Hidden zero-width characters detected — may conceal content…pected,a=S(e.input),s=o[a]??a;return/^[A-Z]/.test(e.expected)?`ورودی نامعتبر: می‌بایست instanceof ${e.expected} می‌بود، ${s} دریافت شد`:`ورودی نامعتبر: می‌بایست …Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07

Cost to the agent

Instructions loaded
≈65 tok
1 file · 29 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

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

What would make this Verified

6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim dhamma-seeker: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Base64 encoding combined with network call≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  5. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  6. 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.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim dhamma-seekerPropose a patch to the maintainer