ClawHub
Back to skill

Security audit

marketing-council

Security checks for vulnerabilities and agentic risk

Overview

This skill provides marketing-advisor simulations using local reference dossiers, with limited and disclosed project-context reading and optional research.

Before installing, be aware that the skill can read product-marketing context files in your project and may perform live research for current claims. Avoid placing highly confidential strategy in those context files unless you want it considered during marketing reviews, and review any custom advisor dossier before saving it.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill description includes a very large set of natural-language trigger phrases such as 'debate this,' 'get multiple perspectives,' and references to famous marketers. These broad cues can cause the skill to activate in situations where the user did not specifically intend to invoke it, leading to misrouting, unnecessary file/context loading, and the application of persona-simulation instructions to unrelated requests.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · evals/evals.json (reported line 22)May include surrounding context.

json
{
      "id": 2,
      "prompt": "What would David Ogilvy say about this headline: 'Revolutionize your workflow with AI-powered synergy'?",
      "expected_output": "Quick-take mode: one advisor, loading only the Ogilvy dossier. Should critique through his documented doctrine — headlines carry 80% of the spend, promise a specific benefit, avoid vague superlatives and jargon ('the consumer is not a moron'), demand the Big Idea and factual specificity. Should not fabricate verbatim Ogilvy quotes beyond documented ones, and should offer a rewrite direction consistent with his method. May hand off to copywriting for execution.",
      "assertions": [
        "Runs quick-take mode with one advisor, not a full council",
        "Applies Ogilvy's documented headline doctrine specifically",