ClawHub
Back to skill

Security audit

Strategic Mentality

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent business-strategy advisor, but it includes recurring Telegram check-ins and stored score tracking without clear opt-in, disable, or privacy boundaries.

Review before installing if you do not want automated Telegram reminders or stored accountability history. Enable it only if you are comfortable sharing business performance metrics through Telegram, and treat prospect research and cold outreach as subject to privacy, anti-spam, and local compliance obligations.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description uses very broad trigger language such as 'any request that benefits from structured strategic thinking,' which can cause the agent to activate for a wide range of ordinary business prompts beyond the user's specific intent. Overbroad activation increases the chance of unintended context loading, unnecessary instruction precedence, and user confusion about why this skill was invoked.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill describes a scheduled Sunday Telegram ping and scorecard workflow without clearly stating that user data may be sent through an external messaging service or that recurring outreach will occur. This creates privacy and consent risks because sensitive business performance information could be transmitted off-platform or users could be contacted unexpectedly without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

Line L74 states that Dutch is the primary language for client communication, which is a natural-language locale policy constraint. The file does not offer a user language choice or frame this as an opt-in, so it can steer outputs toward a fixed language by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The purpose statement frames the skill around Belgian SME owners, and the document then provides objection-handling language primarily in Dutch with English glosses. Because the file does not explicitly offer a language choice or opt-in, it can be read as imposing a specific locale/language by default, which matches the language/locale policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The pre-call checklist instructs collecting and reviewing prospect information from websites, Google reviews, and social media without any guidance on lawful, proportionate, and privacy-conscious handling of that data. While the data appears business/public-facing, the lack of safeguards can normalize overcollection, profiling, or misuse of third-party information during sales preparation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.