Back to skill

Security audit

Newsletter Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a newsletter planning and audit skill that gives advisory workflow guidance and requires approval before live email-system changes.

Installers should treat this as an advisory newsletter operations skill. Review any generated plans before applying them, and require explicit human approval before live sends, contact imports, suppression changes, DNS/authentication changes, provider migrations, or production automation edits.

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
  • 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
89% confidence
Finding

The manifest says to use the skill whenever an AI agent needs to 'plan, review, implement, audit, or improve email work' and lists broad triggers like 'issue planning' and 'editorial calendars.' In a manifest, this activation language is expansive and lacks exclusion conditions or negative examples, which increases the chance of unintended invocation for general email or content-planning conversations.

Content

No source excerpt is available for this finding.