MCP Observatory
github re-analysis due

MukundaKatta/mcp-stack

github

Inject, parse, and strip [N] citation markers in RAG outputs.

maintainer
MukundaKatta
license
—
first seen
2026-06-03
last seen
2026-06-03
releases · 30d
0
short id
risk 24/100 · heuristic grade
B low
  • recent driftinferred+20
  • tool safetyinferred+12
  • trust mitigatorsmixed−8

inferredmixed

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 10m ago · see ecosystem CVEs →

risk trajectory 2 movements
  • B · 16 → B · 24
  • B · 28 → B · 16
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 1 findings · grade factor +12
  1. highhidden prompt content

    1 file(s) with hidden prompt content: MukundaKatta-mcp-stack-6fad5bb/packages/csv-tools-mcp/README.md (hidden-unicode): "LLMs ask for "the CSV parsed" and silently miss edge cases…

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

analyzed commit 6fad5bb · analyzer v17 · 3d ago

skills & prompt files 1

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/github:MukundaKatta/mcp-stack/badge.svg)](https://mcpobservatory.com/servers/github:MukundaKatta/mcp-stack/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 MukundaKatta.