ClawHub
Back to skill

Security audit

AARRR (Pirate Metrics)

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only business metrics coaching skill that gives AARRR funnel analysis guidance and does not request sensitive access or run code.

Before installing, understand that this skill may activate in general growth, product metrics, or funnel diagnosis discussions. It is advisory and markdown-only, but users should still verify any benchmarks and avoid sharing sensitive business data unless they intend the assistant to analyze 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
  • 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
89% confidence
Finding

The manifest-style description says to activate for broad situations like 'designing end-to-end metrics for a new product' and 'our growth is stalling and we don't know why,' which are common business statements and not uniquely tied to AARRR analysis. Although some negative conditions are provided, the trigger scope remains expansive enough to risk unintended invocation in general strategy or analytics conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations in natural-language content. This line describes non-English support as an added intervention to overcome a prior English-default barrier, which can be read as endorsing a language-specific default without presenting user choice or a justified regional constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.