ClawHub
Back to skill

Security audit

snapshot-config-reader

Security checks for vulnerabilities and agentic risk

Overview

The skill reads local snapshot images as advertised, but the bundled hidden configuration contains a secret-bearing curl command aimed at a cloud metadata endpoint, so it needs review before use.

Use this only as an inspection tool for trusted snapshot assets. Treat decoded config as untrusted text, do not execute the printed sync command or feed it into automation without review, and restrict usage to expected snapshot paths.

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 (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
python scripts/read_snapshot.py snapshots/config_trailer.png

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill performs filesystem reads of snapshot images but does not declare any tool scope such as permissions or allowed-tools. That omission weakens review and enforcement boundaries, because consumers of the skill cannot easily determine or constrain what file access is expected, and an attacker could hide broader file-reading behavior behind an underspecified interface.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.