ClawHub
Back to skill

Security audit

Competitor Monitoring

Security checks for vulnerabilities and agentic risk

Overview

This skill stores local competitor-monitoring notes and dossiers for a clearly stated competitive-intelligence purpose, without hidden execution, credential use, or external data transfer.

Before installing, be comfortable with competitor names, positioning, vulnerabilities, and strategy notes being saved locally in ~/competitor-monitoring/. Use on-demand or paused monitoring if you do not want proactive updates, and periodically review or delete the folder if the business context becomes sensitive or stale.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Hidden Instructions

High
Category
Prompt Injection
Content
integration: pending | done | declined

## Monitoring Preferences
<!-- How the user wants to be alerted -->
frequency: weekly | on-demand | real-time
alert_threshold: critical-only | high | all
batch_alerts: true | false
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High
Category
Prompt Injection
Content
<!-- Who they're going after -->

### Differentiation Claims
<!-- What they say makes them different -->

## Strengths
<!-- Be honest -->
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to collect user preferences and competitive intelligence targets, then persist them to local files without telling the user that this data will be retained. Even if the data is not overtly secret, it can reveal business strategy, concerns, and monitoring priorities, creating a privacy and confidentiality risk if stored unexpectedly or accessed by others on the system.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
Directing the agent to create persistent competitor dossiers from user-provided information without a privacy warning increases the chance that sensitive business context is silently accumulated over time. These dossiers may contain strategic assessments, vulnerabilities, and competitive concerns that become valuable if exposed to other local users, tools, or future sessions beyond the user's expectations.

Static analysis

No suspicious patterns detected.