prjct-cli
npm
v4.25.1
Source verified
Published by prjct-app — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
The agentic harness for AI coding agents — work cycles, bounded RAG context, persistent memory, guardrails, and performance evals.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
In the server's implementation (`dist/bin/core-chunks/chunk-HZTC77KI.mjs:7`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: .*\.(?:pem|key|p12|pfx)|id_rsa|id_ed25519|credentials\.json|auth\.json)$/i,ee=/(?:^|\/)(?:\.ssh|\.gnupg|\.aws|\.config\/
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/chunk-HZTC77KI.mjs
In the server's implementation (`dist/bin/hook-chunks/chunk-2E6JLR2S.mjs:8`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: .*\.(?:pem|key|p12|pfx)|id_rsa|id_ed25519|credentials\.json|auth\.json)$/i,Ot=/(?:^|\/)(?:\.ssh|\.gnupg|\.aws|\.config\/
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/hook-chunks/chunk-2E6JLR2S.mjs
In the server's implementation (`bin/prjct.cjs:11`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: Process = require('node:child_process') const fs = require('node:fs') const os = require('node:os') const path = require
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/prjct.cjs
In the server's implementation (`dist/bin/core-chunks/ab-3VUQJGO4.mjs:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: e,spawn as Oe}from"node:child_process";import G from"node:fs";import k from"node:fs/promises";import $e from"node:os";im
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/ab-3VUQJGO4.mjs
In the server's implementation (`dist/bin/core-chunks/agent-LRU4TTKX.mjs:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: xecFile as ft}from"node:child_process";import S from"node:fs";import{promisify as gt}from"node:util";function b(t){retur
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/agent-LRU4TTKX.mjs
In the server's implementation (`dist/bin/core-chunks/auto-updater-ETKWRLKZ.mjs:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: f,spawn as w}from"node:child_process";import r from"node:fs";import o from"node:path";var d=e(()=>o.join(c(),"state"),"
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/auto-updater-ETKWRLKZ.mjs
In the server's implementation (`dist/bin/core-chunks/bin-commands-NASQLNW6.mjs:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: n:l}=await import("node:child_process"),d=l("tail",["-n",String(r),"-f",n],{stdio:"inherit"});process.on("SIGINT",()=>d.
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/bin-commands-NASQLNW6.mjs
In the server's implementation (`dist/bin/core-chunks/chunk-3DDHVWTV.mjs:8`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: n:c}=await import("node:child_process"),l=c("/bin/sh",["-c","command -v prjct >/dev/null 2>&1 && prjct gauntlet >/dev/nu
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/chunk-3DDHVWTV.mjs
In the server's implementation (`dist/bin/core-chunks/chunk-65R3C7IA.mjs:15`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: t.","","### Continue vs spawn (multi-agent)","","| Situation | Action | Why |","|---|---|---|","| Explore already loaded
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/chunk-65R3C7IA.mjs
In the server's implementation (`dist/bin/core-chunks/chunk-A6IDYEDB.mjs:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt{spawn as W}from"node:child_process";import se from"node:path";var Y=6e4,G=500,oe=2e3;function j(e,a){try{process.plat
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/chunk-A6IDYEDB.mjs
In the server's implementation (`dist/bin/core-chunks/chunk-HZTC77KI.mjs:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: xecSync as qe}from"node:child_process";import ot from"node:fs/promises";import V from"node:path";import R from"chalk";im
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/chunk-HZTC77KI.mjs
In the server's implementation (`dist/bin/core-chunks/chunk-LBVVLD7L.mjs:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: K,spawn as $}from"node:child_process";import{promisify as C}from"node:util";async function G(e){try{process.platform===
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/bin/core-chunks/chunk-LBVVLD7L.mjs
Each tool and what it can reach — statically extracted from the published source.
prjct_spec_getingests untrusted inputprjctno sensitive capabilityprjct_analysisno sensitive capabilityprjct_architectureno sensitive capabilityprjct_capture_inboxno sensitive capabilityprjct_cochangeno sensitive capabilityprjct_context_tiersno sensitive capabilityprjct_cost_addno sensitive capabilityprjct_dead_codeno sensitive capabilityprjct_developerno sensitive capabilityprjct_guardno sensitive capabilityprjct_historyno sensitive capabilityprjct_impact_analysisno sensitive capabilityprjct_import_graphno sensitive capabilityprjct_mem_forgetno sensitive capabilityprjct_mem_listno sensitive capabilityprjct_mem_saveno sensitive capabilityprjct_mem_similarno sensitive capabilityprjct_project_factsno sensitive capabilityprjct_qano sensitive capabilityprjct_record_decisionno sensitive capabilityprjct_record_factno sensitive capabilityprjct_record_gotchano sensitive capabilityprjct_record_learningno sensitive capabilityprjct_related_contextno sensitive capabilityprjct_relevant_filesno sensitive capabilityprjct_safe_artifactsno sensitive capabilityprjct_search_symbolsno sensitive capabilityprjct_session_resumeno sensitive capabilityprjct_signalsno sensitive capabilityprjct_signaturesno sensitive capabilityprjct_skillsno sensitive capabilityprjct_spec_apply_deltano sensitive capabilityprjct_spec_auditno sensitive capabilityprjct_spec_createno sensitive capabilityprjct_spec_link_taskno sensitive capabilityprjct_spec_listno sensitive capabilityprjct_spec_record_reviewno sensitive capabilityprjct_spec_set_statusno sensitive capabilityprjct_spec_shipno sensitive capabilityprjct_spec_updateno sensitive capabilityprjct_spec_validateno sensitive capabilityprjct_task_set_statusno sensitive capabilityprjct_task_startno sensitive capabilityprjct_task_statusno sensitive capabilityprjct_trace_pathno sensitive capabilityprjct_workflow_listno sensitive capabilityprjct_workflow_rulesno sensitive capabilityprjct_workflow_statusno sensitive capabilityScan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v4.25.1 latest |
A 94/100 | 12 | 1.13.0 | 2026-09-07 |
v4.23.0 |
A 94/100 | 11 | 1.13.0 | 2026-09-06 |
v4.18.4 |
A 94/100 | 11 | 1.13.0 | 2026-09-04 |
v4.15.0 |
A 94/100 | 11 | 1.13.0 | 2026-09-01 |
v4.13.0 |
A 94/100 | 11 | 1.13.0 | 2026-08-31 |
v4.11.0 |
A 94/100 | 11 | 1.13.0 | 2026-08-30 |
v4.10.0 |
A 94/100 | 11 | 1.13.0 | 2026-08-27 |
v4.8.1 |
A 94/100 | 11 | 1.13.0 | 2026-08-25 |
v4.8.0 |
A 94/100 | 11 | 1.12.1 | 2026-08-22 |
v4.3.0 |
A 94/100 | 11 | 1.12.1 | 2026-08-21 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan prjct-cli --online
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.