ClawHub
Back to skill

Security audit

PostHog

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed PostHog integration that uses Maton for authenticated API access and clearly warns about sensitive data, writes, automation, and persistent forwarding.

Before installing, be comfortable granting Maton access to the selected PostHog account. Prefer OAuth and read-only scopes where possible, confirm every write or new connection, and treat session recordings and person records as sensitive. Be especially deliberate before creating hosted functions, triggers, destinations, or any third-party forwarding because those can keep running until deleted.

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)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says this skill is for PostHog analytics, feature flags, session recordings, and experiments, and explicitly says PostHog is not an event source while trigger references are shared platform material. This file documents Linear webhook event ingestion and scoping, which is a separate third-party source capability not justified by the skill's stated PostHog purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.