ClawHub
Back to skill

Security audit

Marketing Designer: Creative Strategy Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing guidance skill made of Markdown instructions, with no code, persistence, credential use, or hidden execution behavior found.

Before installing, treat this as a creative marketing assistant with a strong point of view. Review outputs for brand fit, audience language preference, and factual accuracy of any marketing claims or metrics, especially for Frutero-specific work.

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
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list is very broad and includes common phrases like 'improve copy,' 'marketing strategy,' and 'pitch deck,' which are likely to appear in many ordinary conversations. That can cause unintended activation of this skill, leading the agent to apply specialized instructions or load extra reference material in contexts where the user did not explicitly request it, increasing prompt-routing risk and reducing predictability.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The Frutero section hard-codes a 'Spanglish swagger' voice for related materials without indicating that this tone is conditional on user preference, audience, locale, or brand approval. In practice, this can produce unintended or culturally mismatched outputs, create reputational risk, and override user instructions about tone or inclusivity.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The line states 'Purely English' is something the brand should not sound like, which effectively requires bilingual or Spanish-inclusive output. This is a natural-language locale/language policy constraint, and the file does not indicate user choice or opt-in for language preference.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger descriptions for major patterns are broad and can match common user requests like copy improvement, strategy, or proposal review without clear boundaries. In an agent system, ambiguous activation can cause this skill to engage when a more appropriate or safer specialized skill should handle the request, leading to scope confusion and potentially lower-quality or misaligned outputs.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The quick-tactical-question trigger relies on subjective wording like 'specific, narrow question' and does not state when the agent must escalate to a fuller strategic response. This can produce inconsistent behavior, where complex or high-stakes requests receive oversimplified advice, increasing the risk of poor decision support or incomplete guidance.

Content

No source excerpt is available for this finding.