Back to skill

Security audit

Client Communication Drafter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward writing assistant for freelancer client messages and does not request tools, credentials, persistence, or automatic sending authority.

Installers should treat the generated emails as drafts to review before sending, especially payment reminders that cite UK late-payment law or current interest rates. The skill does not appear to access private data or take actions on its own.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation description is broad enough to match many ordinary writing or messaging requests, which can cause the skill to trigger outside narrowly intended freelancer-client scenarios. That increases the chance of prompt hijacking of general conversations and can override more appropriate system behavior or routing for unrelated communication tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The rule 'UK English by default' imposes a locale choice unless the user specifies otherwise. This is a natural-language policy concern because it defaults users into a specific language variant rather than offering a neutral default or explicit opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.