Skills/npm/ruflo

ruflo@3.79.1

VERIFIED

Publisher claims: "Ruflo - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher ruvnet · publishing for 528 daysInstalls 359KLast detonated 34 min ago
$claude mcp add ruflo -- npx -y ruflo
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

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the code
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Reasonable to connect. No credential asked for, no third-party host named, Server started and answered tools/list.

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 3.79.0

vet-skills diff ruflo 3.79.0 3.79.1

In the sandbox, this version reached for nothing 3.79.0 did not. Compared from the two recorded runs, not from source.

3.79.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only. Only one of the two runs produced a tool list; tools are not compared.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-20 and scored it 86/100 (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 · 58 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
37sprocessdependency install exit 0
57sfilesystemread ~/work/.claude/settings.json · ~/work/.mcp.json · ~/.claude/settings.json · ~/.mcp.json outside project
57sprocessexec /app/apps/web/node_modules/.bin/agent-browser
57sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/agent-browser
57sprocessexec /app/node_modules/.bin/agent-browser
57sprocessexec /pnpm/agent-browser
57sprocessexec /usr/local/sbin/agent-browser
57sprocessexec /usr/local/bin/agent-browser
57sprocessexec /usr/sbin/agent-browser
57sprocessexec /usr/bin/agent-browser
57sprocessexec /sbin/agent-browser
57sprocessexec /bin/agent-browser
57sclaimed393 tools: agent_execute, agent_health, agent_list, agent_logs, agent_pool, agent_spawn, agent_status, agent_terminate, agent_update, agentdb_batch, agentdb_causal-edge, agentdb_causal-edge-delete, agentdb_causal-node-delete, agentdb_consolidate, agentdb_context-synthesize, agentdb_controllers, agentdb_episode-delete, agentdb_episode-get, agentdb_episode-list, agentdb_episode-recall, agentdb_episode-update, agentdb_feedback, agentdb_graph-pathfinder, agentdb_graph-query, agentdb_health
57stoolsf2e4d8b0eeaa6450
57stools7859fcee22844010
57stools905ab5d3829ea816
57stools9aa4299bbad82610
57stools5346fdd216492405
57stools0c0459bd93798982
57stoolsd47dc058cf433a18
57stools98aff647acf3d61b
57stoolsc2355bb472bbc560
57stools93ba2f2a3fe79659
57stoolsd6c408135f14d79d
57stools17f50ba3d919a451
57stools70929c679fb48f17
57stools47dcb4889fa241b3
57stools471d393ba6f3b3fb
57stoolsc0d29d180de0a5ab
57stools0674885e2380eb9c
57stools5f5b498cab04dd65
57stools278184ce48ab1f34
57stoolsaf263038f9b3204d
57stoolsa842e5f113e2b2c7
57stoolsfe6589f968ad7740
57stools27c3234b72c18b50
57stools4ec64a9479371a85
57stools7cb80ad4ce534d53
57stools3d42af4421981f46
57stoolsa4a0ee4443ffcc46
57stools03a727d61085edf2
57stools8895ebcf81926fc8
57stools375a4fae2b7d47fe
57stools55da0c1d4890f3b3
57stools7aedd6b5647c10cf
57stools7499ac369d17904c
57stools4be11fec4b98e1be
57stools4b7bdc9415ec90f4
57stools35afceb7527f5aa5
57stools07bbb937015c6047
57stools571c6eca8fe715c0
57stools677bcf318c7388e1
57stools814632b817395bc0
57stools2737cae053542e81
57stools5a77af1e7bccd6b7
57stoolsd8339704d613fe02
57stools4f12b8ad9ba8a5cf
57stools845dcd679c6c58ee
57stoolsb97c9cd2bcbc02c4
57stools0f2ec5f36e9654ff
57stoolscf16cdf645d38a11
57stoolsfca20faa145816a7
57stools8b30deb318390cd6
57stools63cc677e389972e1
57stools6e876ac24fc8a860
57stoolsd41171963c34e2b1
57stools0aa3a9770ba51d0c
57stoolsee7ee1657dbea4b9
57stools13a52a5093e0738d
57stools2efca74da5c413b3
57stools0f23f919bea60ce5
57stoolsa78c0d2cfeeda274
57stools1434880cc7190a6c
57stoolse356b971c851b9c6
57stools985a5615dd87f45c
57stools0b8f6caefb270ce4
57stoolsc58b8a69802fb048
57stools5ad69619471fc4cc
57stoolsfe03fa411b303a0f
57stoolsed39858ed072aa1a
57stools9c474d7d4d7bbcb4
57stools834ad2228a2b5119
57stools6a5698825e519cc3
57stools48d9effb1d677ca0
57stools21d8636a49ccd3f1
57stoolsebf7471747324ed8
57stools8df1a7fc0cbb9157
57stools2b4ad0e761822ff6
57stools806b6103b35e0970
57stools08addc8ab671fb5d
57stoolsfd9edf3f04e7b2ab
57stoolsa8a16a70b104ce9a
57stools86b3facf86f1fd24
57sprocessscript backend runs setup only
57sprocessno install scripts to re-run

Static findings

HIGH
Tool description instructs the agent: credential exfiltration instructionmcp:tools/x_federation_channel_accept:1 · Instruction aimed at the agent: credential exfiltration instructiony granted you a channel. Asking them to send you the key directly is wrong because it exposes a bearer secret in a channel you do not control. {"type":"object",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST01
HIGH
Tool description instructs the agent: section addressed to the agentmcp:tools/wasm_agent_create:2 · Instruction aimed at the agent: section addressed to the agent:{"type":"string","description":"System instructions for the agent"},"maxTurns":{"type":"number","description":"Max conversatiFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Unpinned dependencybin/ruflo.js:35 · Unpinned dependency'Stop running Ruflo MCP servers and their hosts, then reinstall with npm install -g ruflo@latest.'Fix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06

Cost to the agent

Instructions loaded
≈79 tok
1 file · 4 in bundle
Tool list per prompt
≈77,478 tok
393 tools · 197 per tool
Handshake
6031 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 377

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.