ClawHub
Back to skill

Security audit

tcms-planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed content-planning helper that reads relevant planning sources and writes topic briefs, with no evidence of hidden execution or data exfiltration.

Install this if you want an agent to read your content calendar and related knowledge-base files to create advisory topic briefs. Review generated briefs before using them downstream, and keep project paths scoped so the agent reads only the intended planning materials.

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
Confidence
91% confidence
Finding
The Chinese read_when triggers are broad enough to match generic planning or review requests, which can cause this skill to activate outside its intended narrow scope. Because the skill has file read/write capabilities, over-broad routing increases the chance of unintended invocation, unnecessary access to project files, and creation of planning artifacts in contexts where another skill or a human decision would be more appropriate.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The English triggers 'review content calendar for topic gaps' and 'generate a topic brief from knowledge-base updates' are insufficiently constrained and may overlap with ordinary editorial review, strategy, or calendar-management requests. In an agent-routing environment, ambiguous activation can misroute tasks to this skill, leading it to read project files and write briefs even when the user did not specifically intend to invoke topic-selection behavior.

Static analysis

No suspicious patterns detected.