ClawHub
Back to skill

Security audit

Bytesagain Doc Summarizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local document summarizer/analyzer that reads user-specified text files and does not show network access, persistence, credential use, or destructive behavior.

Install only if you are comfortable letting the skill read the document files you explicitly ask it to analyze. Be aware that the bundled script appears to have a functional quoting bug around file arguments, but that is reliability risk rather than evidence of malicious behavior.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The code generally aligns with the stated document summarization/analysis purpose and does not use external APIs or unrelated resources. However, there is a description-behavior mismatch in both directions: the implementation includes capabilities not mentioned in the description (outline extraction and detailed text statistics), while a declared use case ('checking document quality') is not actually implemented in any meaningful way. These are material enough to mark as a mismatch, though the primary purpose remains close to the declaration.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

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.

Static analysis

No suspicious patterns detected.