Back to skill

Security audit

Digital Marketing

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing-planning skill with optional, disclosed local continuity storage and no evidence of hidden execution, exfiltration, or account-changing behavior.

Install only if you want a broad digital marketing assistant. Use the continuity folder and main-memory activation only when you want ongoing help, and avoid storing credentials, account access details, proprietary raw data, or sensitive customer information in the local notes.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · market-model.md (reported line 40)May include surrounding context.

md
| Objection | the most likely reason not to act |
| Offer | demo, audit, lead magnet, sale, trial, consultation |

## Output Rule

Every campaign should be traceable back to this structure:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The setup instructs activation for broad categories like digital marketing, launches, funnels, and channel strategy, which substantially overlap with general business-advice requests. That can cause the skill to activate in conversations where the user did not intend to invoke specialized marketing behavior, increasing the chance of inappropriate memory use, overreach, or unwanted steering of the conversation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs the agent to learn activation preferences dynamically and save them in main memory without a strict trigger boundary or exclusion conditions. This creates persistent over-broad activation risk: once inferred, the skill may appear for loosely related requests and influence future sessions beyond the user's immediate intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation guidance says to use this skill whenever the user wants 'viral growth, creator-style marketing, or faster message testing,' which are broad, high-level intents rather than specific trigger conditions. It does not define boundaries, exclusions, or negative examples, so the skill could be invoked for many ordinary marketing conversations unintentionally.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The template instructs creation of a persistent local memory file containing company, audience, offer, channel, and constraint data, but it does not clearly warn that this information will be stored across sessions on disk. That can lead users to disclose sensitive business or project information without informed consent, especially because the persistence is framed as a normal workflow feature.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The optional support files expand persistence to campaigns, experiments, signals, metrics, and reusable lessons, which may include commercially sensitive performance data and strategic information. Without a clear warning and consent gate, the skill may encourage long-term storage of higher-sensitivity marketing intelligence than users realize.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.