ClawHub
Back to skill

Security audit

SDS/MSDS Risk Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small SDS/MSDS hazard-code scanner with disclosed local Python execution and no evidence of hidden access, persistence, network use, or credential handling.

Install only for SDS/MSDS-style chemical safety extraction. Treat results as a structured aid, not a substitute for reviewing the source datasheet or professional safety guidance, especially because the included script is simple and the skill is marked draft.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill’s invocation guidance expands beyond SDS/MSDS extraction into generic 'evidence insight' work, which can cause an orchestrator or user to select this skill for tasks outside its documented safety and parsing boundaries. That scope drift increases the chance of processing unintended files or producing misleading outputs under the authority of a chemistry-focused skill, even though the file also contains some limiting language elsewhere.

Content

No source excerpt is available for this finding.