Back to skill

Security audit

UAE clinic-marketing-uae

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown guidance skill for UAE clinic marketing, with no executable code, credential use, persistence, or hidden data access.

Before installing, treat this as jurisdiction-specific marketing guidance rather than legal advice, and ask the agent to confirm clinic stage, specialty, location, and preferred languages when needed. There is no evidence that the skill executes code or accesses private data.

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger list is very broad and includes many generic healthcare marketing phrases, which can cause the skill to activate in conversations where the user did not intend to invoke this specialized guidance. Unintended invocation can override more appropriate instructions, create compliance risk, and surface domain-specific recommendations in the wrong context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill prescribes Arabic and English as mandatory for the audience without checking the user's actual preference or context. While not directly a security flaw, this can improperly constrain outputs, reduce user autonomy, and cause the agent to act on assumptions rather than explicit user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.