Back to skill

Security audit

code-crawler

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign for repository code-relationship questions, while noting unpinned package commands and incomplete review of some referenced paths.

Before installing, consider whether you are comfortable running unpinned npm packages and registering an MCP server in your client configuration. The scan covered all three listed components, but its analysis is marked partial because several path-like references could not be resolved, so the evidence is not complete.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding

The supplied chunk performs client setup, not code-relationship analysis. Although configuring the named MCP server is related to the declared workflow, changing Cursor's MCP configuration is a distinct capability not disclosed in the description. No graph queries or question-answering behavior appear in the supplied code.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The documented npx skills command can download and execute an unpinned npm package with the user's permissions. Although this is an installation helper rather than the MCP server itself, a compromised or malicious future release could access repository files or credentials; the document provides no evidence that such compromise has occurred.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx add-mcp'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The registration command invokes an unpinned add-mcp utility and names an unpinned server package. Compromise of either distribution could introduce arbitrary local code execution, while registration can persist the server launch configuration; the explicit requirement to ask before config changes reduces unauthorized setup risk but not dependency risk.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx add-mcp'.

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The concrete Cursor setup example executes an unversioned npm helper and registers an unversioned MCP server. These are legitimate setup operations, but a substituted or compromised release could execute with local user privileges and persist through the client configuration.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx add-mcp'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

Even the informational npx add-mcp list-agents command executes package code, so omitting a version exposes it to the same mutable-dependency risk as installation. Its intended behavior only lists clients, making the workflow benign, but that does not constrain what a compromised package could do.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y @nithin554/code-crawler'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The crawl command uses npx -y to execute an unpinned package without an installation confirmation prompt. Because crawling operates on the repository, a compromised release could read sensitive source files or perform other actions with the user's permissions; the earlier MCP configuration repeats the same unpinned execution pattern.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 189)May include surrounding context.

md
call is not what the annotation promises when either is set: `inert: true` means
  self-invocation bypassed the proxy, `proxyBlocked` (`private`, `static`, `final`,
  `final-type`) means the container could never have honoured it. Do not report an
  annotated method as transactional or asynchronous without checking these.
- An edge with `alternatives` is an unresolved *choice*, not an unresolved call: the call site
  is proven but several overloads matched equally, and the target is the first declaration with
  the rivals listed. Confidence is capped at `0.6`. Report both rather than asserting the one

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 228)May include surrounding context.

md
## Do not

- Crawl a monorepo to answer a question about one file.
- Report "no callers" or "dead code" without checking `confidence` (where present) and
  `external` on the edges you did get, and without noting whether dispatch edges were
  followed.
- Treat `find_unresolved` as a bug list. It is a coverage report; some entries are