Back to skill

Security audit

stock-screener

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this stock screener skill suspicious with medium confidence, mainly because the scanner reports that requested technical filters may be skipped when analysis fails.

Treat the results as requiring review before installing. Consider whether you are comfortable with technical filters being bypassed on analysis failure, and review the skill's tool access and dependency installation process. The scan was partial: 9 of 10 components were scanned, and static analysis of scripts/screen.js was limited, so the evidence is incomplete.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Requested technical filters are silently bypassed in returned results when technical analysis fails.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

When technical analysis fails, the catch block logs an error but allows execution to return stocks without applying the requested technical filters. This fail-open behavior can mislead users or downstream automation into treating unverified financial results as matching their criteria, especially when consumers capture stdout but not stderr.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
76% confidence
Finding

The caret range permits different compatible iconv-lite releases to be selected during installations that do not enforce a trusted lockfile. This creates a conditional supply-chain risk if an eligible release is compromised, but the supplied manifest does not demonstrate a compromised dependency or establish whether a lockfile exists.

Content

Scanner excerpt · package.json (reported line 10)May include surrounding context.

json
"test": "node index.js --limit 5"
  },
  "dependencies": {
    "iconv-lite": "^0.7.2",
    "minimist": "^1.2.8"
  }
}

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
76% confidence
Finding

The caret range allows installations without an enforced lockfile to resolve a newer compatible minimist release. A compromised eligible release could introduce attacker-controlled code into the skill, although neither compromise nor the absence of a lockfile is established by this source.

Content

Scanner excerpt · package.json (reported line 11)May include surrounding context.

json
},
  "dependencies": {
    "iconv-lite": "^0.7.2",
    "minimist": "^1.2.8"
  }
}