MCP Observatory
npm analyzed 2.44.2

prjct-cli

v2.44.2
npm

Context layer for AI agents. Project context for Claude Code, Gemini CLI, and more.

maintainer
jlopezlira
license
MIT
first seen
2026-06-01
last seen
2026-06-14
releases · 30d
70
short id
risk23/100 · heuristic grade
B low
  • capability exposureinferred+22
  • inherited (deps)attested+15
  • trust mitigatorsmixed−14

attestedinferredmixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 12m ago · see ecosystem CVEs →

capability exposuregrade factor +22
Inferred surface — each links to servers holding it:
vulnerabilities1 CVEs · grade factor +0
NONE
Malicious code in prjct-cli (npm) affects []npm

inherited (deps) · grade factor +15

inherited via dependencies3
HIGH
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse via @modelcontextprotocol/sdk · 1 hop CVE-2026-25536 fixed in 1.26.0
HIGH
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability via @modelcontextprotocol/sdk · 1 hop CVE-2026-0621 fixed in 1.25.2
HIGH
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default via @modelcontextprotocol/sdk · 1 hop CVE-2025-66414 fixed in 1.24.0
tool safetyall quiet

No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.

skills & danger signalsnpm-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v2.44.2 · analyzer v17 · 2d ago

skills & prompt files 5

embed badgereadme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:prjct-cli/badge.svg)](https://mcpobservatory.com/servers/npm:prjct-cli/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of jlopezlira.