vibe-shield — security scanner for AI-generated code
NPM · @VIBEFOUNDRY/VIBE-SHIELD
Scans AI-written code for leaked secrets, unguarded routes and missing RLS.
Available components
Last scanned (17 hours ago)
Scores higher than 49% of npm servers
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability73
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 592 tokens (~197/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
- Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 17 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 2.1.2 → 2.1.3 functional
- 16 Nov 26 +3
- Stability: unverified → 0.20 ▲ functional
- 11 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 10 Nov 26 54
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/@vibefoundry/vibe-shield@2.1.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
vibe_shield_audit_skills Audit agent skills and MCP configuration for poisoning ~162
Audits .claude/skills, .cursor rules, .cursorrules, AGENTS.md, CLAUDE.md and MCP config files (mcp.json, .mcp.json) for agent-poisoning: hidden Unicode instructions, credential exfiltration commands, reads of .env or ~/.ssh, unpinned MCP servers, literal credentials and safety-override language. Call this whenever you add or modify an agent instruction file, a skill, a Cursor rule or an MCP server config.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum findings to return. Default 25. |
| paths | array | – | Specific agent files or directories to audit. |
| target | string | – | Project root to audit. Default: the server working directory. |
No output schema declared.
No examples provided.
vibe_shield_explain_rule Explain a detection rule ~105
Returns the full documentation for one rule id or slug: severity, confidence, CWE, why it is exploitable, the vulnerable code shape, the fixed code shape, ordered remediation steps and references. Use this when you need to understand a finding before fixing it, or when the user asks what a rule means.
| Name | Type | Req | Description |
|---|---|---|---|
| ruleId | string | yes | Rule id or slug, e.g. "VSB-CLIENT-001" or "public-env-secret-exposure". |
No output schema declared.
No examples provided.
vibe_shield_scan Scan a project for AI-introduced security bugs ~250
Runs the 60-rule vibe-shield scanner over a project directory or a set of paths and returns the grade, score and every finding with its exact file, line, CWE and remediation steps. Call this after writing or modifying application code — API routes, server actions, database migrations, auth logic, environment variables, LLM calls or webhook handlers — and before reporting a task as complete. Also call it when the user asks for a security review or audit.
| Name | Type | Req | Description |
|---|---|---|---|
| includeDocs | boolean | – | Include Markdown and documentation files. |
| includeTests | boolean | – | Include test, spec and fixture files. |
| limit | integer | – | Maximum findings to return in the text summary. Default 25, 0 for all. |
| paths | array | – | Explicit files or directories to scan, instead of the whole project. |
| rules | array | – | Restrict to these rule ids or prefixes, e.g. ["VSB-CLIENT-001"] or ["VSB-DB-*"]. |
| severity | string | – | Only return findings at or above this severity. |
| target | string | – | Directory or file to scan. Relative paths resolve against the server working directory. Default: the working directory. |
No output schema declared.
No examples provided.
How do I install the vibe-shield — security scanner for AI-generated code MCP server?
vibe-shield — security scanner for AI-generated code runs locally as an npm package, launched with npx -y @vibefoundry/vibe-shield mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @vibefoundry/vibe-shield
claude mcp add avivgerz-hue-vibe-shield -- npx -y @vibefoundry/vibe-shield mcp
What is the vibe-shield — security scanner for AI-generated code MCP server?
vibe-shield — security scanner for AI-generated code is an MCP server listed in the public MCP registry as io.github.avivgerz-hue/vibe-shield. Scans AI-written code for leaked secrets, unguarded routes and missing RLS. This page covers its npm package (@vibefoundry/vibe-shield).
Is the vibe-shield — security scanner for AI-generated code MCP server safe to use?
vibe-shield — security scanner for AI-generated code scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the vibe-shield — security scanner for AI-generated code MCP server expose?
vibe-shield — security scanner for AI-generated code exposes 3 tools: vibe_shield_scan, vibe_shield_audit_skills, vibe_shield_explain_rule. Their descriptions and schemas cost roughly 517 tokens of context every time the server is loaded.
Is the vibe-shield — security scanner for AI-generated code MCP server still maintained?
vibe-shield — security scanner for AI-generated code is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the vibe-shield — security scanner for AI-generated code MCP server under?
vibe-shield — security scanner for AI-generated code declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the vibe-shield — security scanner for AI-generated code MCP server?
VerifyMCP ran 16 checks on vibe-shield — security scanner for AI-generated code, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.