ClawHub
Back to skill

Security audit

Marketing Ideas

Security checks for vulnerabilities and agentic risk

Overview

This skill provides SaaS marketing idea guidance and does not request unusual access, run code, or persist changes.

Install this if you want a general SaaS marketing brainstorming helper. Be aware it may activate on broad growth-related prompts, so clarify when you want non-marketing strategy or a more specific channel skill.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is genuinely overbroad: it includes very generic phrases such as 'what else can I try' and 'I don't know how to market this,' which can overlap with broad brainstorming or advice-seeking requests outside a clearly defined marketing context. This can cause the agent to invoke this skill inappropriately, steering conversations into marketing guidance when the user's intent is ambiguous and potentially suppressing more relevant or safer skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The eval explicitly expects the skill to trigger on casual phrasing, which can incentivize broad matching behavior rather than precise intent detection. In a routing or orchestration system, this can cause the marketing skill to activate for vague growth-related prompts where a more specific or different skill should handle the request, leading to misrouting, reduced guardrail effectiveness, and unexpected downstream behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.