Skills/npm/boondmanager-mcp-server

boondmanager-mcp-server@2.19.3

VERIFIED· startup only

Publisher claims: "MCP Server for BoondManager API - 185 tools, 13 prompts, 22 resources (ERP/CRM)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher silamir · publishing for 263 daysInstalls 1,441Last detonated 1 h ago
$claude mcp add boondmanager-mcp-server -- npx -y boondmanager-mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Verified 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

It will ask for
OAUTH_METADATA_PATHConfiguration, not credentials: ENTITY_PATH, TASK_ENTITY_PATH
Where it talks to
boondmanager.com (its own)
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for OAUTH_METADATA_PATH and talks to boondmanager.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --secrets OAUTH_METADATA_PATH=boondmanager.com -- npx -y boondmanager-mcp-server

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

What changed since 2.19.2

vet-skills diff boondmanager-mcp-server 2.19.2 2.19.3

In the sandbox, this version reached for nothing 2.19.2 did not. Compared from the two recorded runs, not from source.

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; startup only; authenticated tool behavior not tested) on 2026-11-15 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 41 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
21sprocessdependency install exit 0
41sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-tQkqyV/task/home/work/acme-api/.claude/skills/boondmanager-mcp-server/dist/services/boond-client.js' } Node.js v22.23.5
41sprocessscript backend runs setup only
41sprocessno install scripts to re-run

Static findings

LOW
Authorization escalation languageREADME.md:878 · Authorization escalation language · informational: not an instruction file| **ChatGPT (connecteurs / Developer mode)** | Ajouter un connecteur MCP distant pointant sur l'URL HTTP ; l'OAuth2 est decouvert via la metadata `/.well-known/oauth-protected-resource`. |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/schemas/index.js:1259 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// is not moved by an update (issue #252; write path not exercised, see CLAUDE.md).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/schemas/index.js:1734 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// PUT /contracts/{id} — issue #252 (write path not exercised, see CLAUDE.md).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/schemas/index.js:1705 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// PUT /provider-invoices/{id} — issue #252 (write path not exercised, see CLAUDE.md).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Destructive file system command detecteddist/tools/resources.js:100 · Destructive file system command detected• **Compétences / outils** : \`tools: [<toolId>, ...]\` (OU par défaut ; pour ET: \`["#AND#", "1", "2"]\`). \`expertiseAreas\`, \`activityAreas\`, \`languages\` (format \`langueId|niveauId\`).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detecteddist/tools/candidates.js:59 · Destructive file system command detected…ivityAreas\`, \`experiences\`, \`trainings\`, \`mobilityAreas\`, \`languages\` (format \`langueId|niveauId\`). • **Sourcing** : \`sources: [<id>]\` (origine du candidat…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/schemas/index.js:1614 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// PUT /payments/{id} — issue #252 (write path not exercised, see CLAUDE.md).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:878 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| **ChatGPT (connecteurs / Developer mode)** | Ajouter un connecteur MCP distant pointant sur l'URL HTTP ; l'OAuth2 est decouvert via la metadata `/.well-known/oauth-protected-resource`. |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filesdist/schemas/index.js:976 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file// write field. See CLAUDE.md → *Timesheets* for what was and was not verifiedFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈62 tok
1 file · 81 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

Not checked against OSV yet; the weekly check has not reached this version.