Skills/npm/converse-mcp-server

converse-mcp-server@4.9.10

CAUTION· not started

Publisher claims: "Converse MCP Server - Converse with other LLMs with chat and consensus tools" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher falldownthesystem · publishing for 476 daysInstalls 6,029Last detonated 7d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try converse-mcp-server` runs it now and prints the full answer.

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

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-07 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.8sprocessdependency install exit 1
1.0sprocessexec /usr/bin/date
1.0sprocessexec /usr/bin/timeout
1.0sclaimedno tools/list reply (exit 0)
1.0sprocessscript backend runs setup only
1.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/config.js:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Priority: .env.test (for test env) > .env (default)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathspackage.json:93 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env.example"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/config.js:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdotenv.config({ path: '.env.test', quiet: true });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/config.js:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Load environment variables from appropriate .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/config.js:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files// Fall back to .env for any missing variablesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injection attemptdocs/ALTERNATIVE_PROVIDERS.md:293 · Prompt injection attempt — model control tokens · informational: not an instruction file · informational: not an instruction file · informational: not an instruction fileprompt: '<s>[INST] Hello [/INST]',Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packagebin/converse.js:15 · npx invocation of non-well-known package — may execute untrusted code// node builtins, so this stays a sub-100ms round trip for `npx converse -v`.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Destructive file system command detectedsrc/providers/claude.js:489 · Destructive file system command detected// Convert messages to SDK input formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/providers/gemini-cli.js:532 · Process kill command — agent can terminate processes// then schedules a post-kill grace timer so we never hang if onExit neverFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/utils/localProviderAuth.js:62 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesreturn existsSync(join(configDir, '.credentials.json'));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsrc/providers/gemini-cli.js:45 · Process kill command — agent can terminate processes// Extra wall-clock grace before the JS-side hard kill fires (ms).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈59 tok
1 file · 73 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

No advisories in OSV for converse-mcp-server@4.9.10 as of 7d ago. This is the package itself, not its dependencies.

What would make this Verified

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim falldownthesystem: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim falldownthesystemPropose a patch to the maintainer