ClawHub
Back to skill

Security audit

Conference Abstract Adaptor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local abstract-formatting script with disclosed file input and optional file output, and I found no hidden network, persistence, credential, or destructive behavior.

Install only if you are comfortable running a local Python script on files you choose. Use non-sensitive abstract files, write outputs to a workspace or temporary directory, and avoid pointing --output at important existing files because the script does not prevent overwrites or path traversal.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill documents file-writing behavior (--output saves adapted content to a file) but does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization gap: an agent or runtime may permit broader filesystem actions than users expect, increasing the risk of unintended or unsafe file writes if the implementation mishandles paths or output locations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.