ClawHub
Back to skill

Security audit

pharmaziegasse

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed informational pharmacy-platform namespace skill with a small local script and no evidence of hidden data access, persistence, or harmful behavior.

Before installing, understand that the skill grants exec for a bundled information script. The inspected version appears low risk and informational, but users who do not want any shell-capable skills can choose to avoid it or request a markdown-only package.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
The manifest requests shell execution capability and includes a script entry, but the stated purpose in this file is pharmacy management functionality rather than a clearly bounded operational need for arbitrary command execution. In an agent skill context, exec materially increases the attack surface because a later prompt or script can invoke host commands, access local data, or chain into additional system actions beyond the declared business purpose.

Static analysis

No suspicious patterns detected.