ClawHub
Back to skill

Security audit

Timothe Growth Calendar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Timothe Growth Calendar helper that can change a user's content calendar and spend credits, but its sensitive actions are mostly scoped and user-directed.

Install this only if you want the agent connected to your Timothe workspace. Before approving work, check the credit cost, the articles or style changes being made, and any future reservations that will generate articles automatically.

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
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description says to use the skill when the user asks about their content calendar, article schedule, planned or published posts, topic clusters, or wants to plan or write SEO articles for their site. These triggers are broad natural-language concepts rather than a constrained invocation scope, which could cause the skill to activate on ordinary content or marketing discussions without clear boundaries.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

md
Treat `plan_cluster` and `generate_article` as actions the user authorizes, not as steps you take to
explore. Say what it will cost and what it will produce, get a clear yes, then call it once. Never
call either one to find out what happens, and never retry after a failure without checking `get_run`
first: the run may have succeeded and the retry would be charged again.

The research tools are different in kind. They are cheap and fast, so once the user has agreed to

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
81% confidence
Finding

The instruction to run research tools 'without asking permission for each one' permits autonomous spending of paid credits after only a general agreement to 'look into a topic.' Even if the tools are described as cheap, they are still billable and can trigger multiple external queries without granular user consent, creating a risk of unauthorized cost and action escalation.

Content

Scanner excerpt · SKILL.md (reported line 94)May include surrounding context.

md
first: the run may have succeeded and the retry would be charged again.

The research tools are different in kind. They are cheap and fast, so once the user has agreed to
look into a topic, run them without asking permission for each one. Do tell them roughly what you
spent when you report back.

## Checking a market before committing to it

Static analysis

No suspicious patterns detected.