muninn@2.3.7

VERIFIED

Publisher claims: "Universal Context Protocol (CXP) for AI agents. v2.3.7 includes the latest high-performance CXP engine (compiled 2026-02-13) with fix for memory amnesia, macOS binary support, and pfeilschnell indexing. Created by @Blackknight1dev." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher endgegnerbert-tech · publishing for 281 daysInstalls 3,940Last detonated 22 min ago
$clawhub install muninn
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-22 and scored it 93/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 24 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
4.0sprocessdependency install exit 0
24sclaimed6 tools: init_project, brain_check, add_memory, search_context, reindex_context, health_check
24stools716e4d540fd92ac3
24stools3b9323bfaafac9ce
24stools7ac2b9c1ce7410c9
24stools6faefd2e07bf78c0
24stools1f7d3c48c05463c3
24stools62e69371aae9d840
24sprocessscript backend runs setup only
24sprocessno install scripts to re-run

Static findings

HIGH
Coercive compliance languageSKILL.md:26 · Coercive compliance languageAs an agent, you MUST follow the "Brain-First" workflow to remain efficient and accurate. The MCP server ensures project safety by validating context before allowing sensitive tool operations.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

No other findings across 3,692 lines in 26 files.

Cost to the agent

Instructions loaded
≈1,806 tok
2 files · 26 in bundle
Tool list per prompt
≈298 tok
6 tools · 50 per tool
Handshake
396 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 56

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

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.