ClawHub
Back to skill

Security audit

PostHog

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent PostHog connector, but its setup instructions include running remote installer scripts without verification.

Before installing, decide whether you trust OOMOL and the `oo` CLI installation path. Prefer installing the CLI manually from verified official instructions, use a least-privilege PostHog connection where possible, and require explicit review before any write or destructive PostHog action.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
95% confidence
Finding

The skill instructs the agent to execute a remote installer via curl ... | bash, which is a classic supply-chain and arbitrary code execution risk. Even though it is framed as first-time setup for a trusted CLI, the pattern executes unaudited code fetched at runtime and is especially dangerous in an agent skill because the skill explicitly allows Bash and may normalize running shell commands automatically.

Content

Scanner excerpt · SKILL.md (reported line 111)May include surrounding context.

Static analysis

No suspicious patterns detected.