io.github.goklab/guardvibe v3.30.0

40D

Security Trust Score

Grade D · Weak posture

Tier 1 · Public sourceHigh confidence · 98%rubric 2.9.0

Declared MCP capabilities

ResourcesPrompts

This server scored D. Run it behind runtime policy enforcement so one bad tool call can't become an incident.

2 issues capping this score

highTool descriptions free of injection markers — 1 marker(s) across 1 tool(s)
mediumNo over-broad / destructive tools — 8 over-broad tool(s)

Reputation4stars0forks2.2kdownloads/mo9open issues35d agolast commit<1yage

Security controls

Deterministic, evidence-backed. Score earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

Fail
Indirect Prompt Injection (IPI) Defensesguard1 marker(s) across 1 tool(s)
Tool/prompt/resource text is free of hidden instructions that could hijack the agent. How many servers fail this?
MCP Tool Description Contains Injection Instructions — 'ignore previous' override
Fix: Remove hidden directives, HTML/comment instructions, and override phrasing from descriptions.
Fail
User-in-the-Loop / Approval Scopeguard8 over-broad tool(s)
No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval. How many servers fail this?
Debug Endpoint Exposes System InformationYAML Parsed with Unsafe LoaderClaude Hook Contains Shell MetacharactersAI System Prompt Leaked in Error Response
Fix: Scope tools narrowly; avoid arbitrary command execution and destructive defaults.
Warn
Strict JSON Schema Enforcementschemas not strict
Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.
Fix: Set additionalProperties:false and require explicit parameters on every tool.
Pass
Tool Definition Integrityguardtool definitions stable; no risky changes in version history
Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns.

Application Security Checks

Warn
Dependencies pinned (lockfile)no lockfile found
A lockfile makes installs reproducible and resistant to silent dependency swaps.
Fix: Commit a lockfile (package-lock.json / pnpm-lock.yaml / poetry.lock).
Warn
Established maintainersingle maintainer
Brand-new / single anonymous maintainers raise takeover and malware risk.
Fix: Publish under an established account/org; add multiple maintainers.
Warn
Has a security policyno security policy
A SECURITY.md gives a private path to report vulnerabilities.
Fix: Add SECURITY.md with a disclosure contact and process.
Pass
No command-injection sinksguardno sinks found
Untrusted tool input reaching a shell yields remote code execution.
Pass
No dynamic code executionguardno sinks found
eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.
Pass
No path traversalguardno sinks found
Naive path checks let tools read/write outside intended directories (EscapeRoute-class).
Pass
No SSRF sinksguardno sinks found
Fetching tool-supplied URLs can pivot into internal networks and metadata services.
Pass
No unsafe deserializationguardno sinks found
pickle/yaml.load/etc. on untrusted data can execute code.
Pass
No committed secretsguardno secrets found
Hardcoded keys/tokens in published source are live credentials an attacker can use.
Pass
Credentials sourced from environmentreads credentials from environment
Reading secrets from env/secret stores avoids hardcoding them.
Pass
No known-vulnerable dependencies1 runtime deps, no known CVEs
Runtime dependencies (parsed from the lockfile) are scanned against OSV.dev for published CVEs. Advisory: flagged dependencies lower the score but don't hard-cap it, since transitive reachability is unproven.
Pass
No install/post-install scriptsguardno install scripts
install hooks run arbitrary code on every consumer at install time.
Pass
Package name not typosquattingguarddistinct package name
Names mimicking popular packages are a common malware delivery vector.
Pass
Published with provenancepublished with provenance
Build provenance attests the artifact was built from the claimed source by CI.
Pass
Actively maintainedrecent commits
Unmaintained servers don't receive security fixes.
Pass
Repository not archivedguardactive
Archived repositories will never be patched.
Pass
Declares a licenseApache-2.0
A clear license is required for legal enterprise use.
Pass
Adoption & popularityestablished adoption
A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.
Not checked
Signed releasesnot evaluated
Signed releases let consumers verify artifacts weren't tampered with.

Transport & Trust Model

Warn
Execution Sandboxingruns natively (no container image)
A container/sandbox image limits blast radius; a server that runs natively has full host access.
Fix: Ship a Dockerfile/Containerfile (or document a sandboxed run) so the server runs isolated.
Warn
Network Exposurebinds 0.0.0.0
Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.
Fix: Bind to 127.0.0.1 by default; never ship open debug endpoints.
N/A
Transport Encryption (TLS)guardno remote endpoints
Plaintext HTTP exposes traffic and bearer tokens to interception.
N/A
IAM / Authentication Scopingno remote endpoints
OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.
N/A
Live Endpoint Reachablenot dynamically scanned
A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.
N/A
Authentication Enforced (live)not dynamically scanned
If the server declares auth is required, it must actually reject anonymous clients. Serving tools to unauthenticated callers is a real exposure.

Tools (81)

get_userfetch_weatherState-Changing GET RequestPlaintext Password ComparisonHTTP Response Header InjectionMissing Referrer-Policy HeaderYAML Parsed with Unsafe LoaderMCP Tool Handler Path TraversalMissing Request Body Size LimitTiming-Unsafe Secret ComparisonRate Limiter Fails Open on ErrorLLM Output Used in Dangerous SinkMissing Permissions-Policy HeaderAI Prompt Injection via User InputMCP Tool Handler Command InjectionPackage Lockfile Excluded from GitMCP Config References file:// ServerSystem Prompt Echoed in API ResponseCSP Missing frame-ancestors DirectiveLLM Output Rendered as Unescaped HTMLOverly Broad Wildcard in allowedToolsTLS Certificate Verification DisabledAI Tool Execute With Unsanitized InputRegular Expression Vulnerable to ReDoSAI Agent with Unrestricted Shell AccessSettings Hook Executes Network RequestsCritical Operation Without Audit LoggingInternal Error Message Exposed to ClientOPENAI_BASE_URL Set to Non-OpenAI DomainPostToolUse Hook Modifies Files SilentlyAI System Prompt Leaked in Error ResponseAuthorization Defaults to Permissive RoleClaude Hook Contains Shell MetacharactersDebug Endpoint Exposes System InformationIn-Memory State in Serverless EnvironmentMCP Tool Handler SSRF via Unvalidated URLMulti-Tenant Query Without Tenant ScopingServer-Sent Events Without AuthenticationStreaming AI Response Rendered as Raw HTMLVector Store Upsert Without AuthenticationAI Tool with Unrestricted Database MutationUnquoted .env Value with Special CharactersWebSocket Connection Without AuthenticationAI Response Rendered via Raw-HTML React PropLangChain Agent Loads Code or Tools From URLObject Injection via Dynamic Property AccessExternal Script Without Subresource IntegrityGoogle Gemini SDK Initialized in Browser CodeLogin Endpoint Without Brute Force ProtectionMCP Config with Overly Permissive Tool AccessMCP Tool Returns Unsanitized External ContentpostMessage Handler Without Origin ValidationANTHROPIC_BASE_URL Set to Non-Anthropic DomainMCP Server env Block Contains Hardcoded SecretSettings Hook Pipes Output to External CommandUser Input Forwarded to LLM Without Length CapFile Content Passed to LLM Without SanitizationState-Changing Endpoint Missing CSRF ProtectionXML Parsing Without Disabling External EntitiesVercel AI SDK Server Action Exposes API Key PathRace Condition: Check-Then-Act Without TransactionAI Assistant Auto-Approve Bypasses Permission PromptMCP Server Pinned to @latest (Unpinned Supply Chain)MCP Tool Description Contains Injection InstructionsDatabase Query Results in LLM Prompt Without BoundaryMCP / Agent Tool-Call Endpoint Without AuthenticationAgent Tool Loop Without max_steps / max_iterations CapAI Host Config Grants Write to Security-Sensitive PathsAI Output Rendered as Markdown Image Without ValidationExternal Fetch Data in LLM Context Without SanitizationUser-Controlled URL in href Without Protocol ValidationAI SDK Tool Returns Fetched Content Without SanitizationAI Tool with Destructive Operations Without ConfirmationUser Input Embedded into Vector Store Without ValidationMCP Server Command Loads From World-Writable or Temp PathVector Store Retrieval Result Interpolated into LLM PromptSupabase Race Condition: Check-Then-Act Without TransactionAPI Key Embedded in Tool Description or System Prompt StringLLM API Key Exposed Via NEXT_PUBLIC / VITE / EXPO_PUBLIC PrefixConversation Messages Array Serialized to Client With System RoleMCP / AI Tool Description Contains Prompt-Injection Markers (OWASP MCP Top 10)