ClawHub
Back to skill

Security audit

Mobile App Launch Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a coaching-only mobile app launch skill with broad advice but no code execution, persistence, credential use, or hidden behavior.

Safe to install as a coaching aid, but treat its store-policy, legal, privacy, health, finance, kids, crypto, and AI-disclosure guidance as planning advice that should be checked against current Apple/Google policies and qualified legal or compliance sources before launch.

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
91% confidence
Finding

The skill activates on very broad product and app-building topics, which can cause it to engage outside its narrow intended scope. Over-broad routing increases the chance of the agent giving authoritative mobile-launch advice in ambiguous contexts, leading to misrouting, policy bypass of more appropriate specialist skills, or unsafe guidance for regulated app categories before sufficient qualification.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The geographic launch scope prompt is broad and unconstrained, which by itself is not dangerous, but in this skill it can encourage globally framed advice without region-specific policy qualification. That can result in incomplete or inaccurate compliance guidance for jurisdictions with materially different privacy, payments, age-gating, or distribution requirements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.