ClawHub
Back to skill

Security audit

Kpi Tree Design Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a plain advisory KPI-tree coaching skill with no executable code or hidden data-handling behavior; the scanner warning appears to be a false positive about ordinary business wording.

This skill is reasonable to install for strategic KPI design. Users should still avoid sharing confidential business metrics unless they are comfortable using them in an AI chat, but the artifact itself does not add code execution, persistence, or external data access.

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
  • 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 (1)

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 · SKILL.md (reported line 56)May include surrounding context.

md
- Revenue: 30-90+ days lag
- Cohort retention: 6-12 months lag
- LTV: 12-36 months lag
- A useful tree has metrics at each lag horizon. **Don't have a tree where everything has 90+ days lag** — you can't manage anything in real-time.

### Metric ownership vs awareness
- **Owned**: a specific person (or small team) can move this metric in <90 days through their daily/weekly actions

Static analysis

No suspicious patterns detected.