ClawHub
Back to skill

Security audit

product-marketing

Security checks for vulnerabilities and agentic risk

Overview

This skill creates a visible product marketing context file and its file access and persistence are disclosed and aligned with that purpose.

Install this if you want marketing skills to share a repo-local product positioning document. Review the generated `.agents/product-marketing.md` before saving because inaccurate positioning, audience, or proof-point details may influence later marketing outputs.

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
94% confidence
Finding

The trigger list is broad and includes generic phrases like 'describe my product,' 'positioning,' and 'who is my target audience,' which can cause this skill to activate in situations where the user did not intend to create or modify shared marketing context. Because this skill writes a persistent file consumed by other marketing skills, accidental invocation can propagate incorrect assumptions or stale context across later tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This eval encourages the skill to trigger on vague language like 'create a product context doc for my app' without tightly constraining when the skill should activate. Over-broad activation can cause the agent to select the wrong skill, perform unintended repository reads/writes, or bypass more appropriate specialized workflows, especially because this skill creates and updates shared context files used by other marketing skills.

Content

No source excerpt is available for this finding.