ClawHub
Back to skill

Security audit

tcms-adapter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed content-adaptation workflow that reads existing drafts or published articles and writes channel-specific marketing drafts, without publishing or persistence.

Install only if you want an agent to transform reviewed or published marketing content into channel-specific drafts. Review generated posts before publishing, especially customer names, data points, and English copy marked for confirmation.

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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The `read_when` triggers include broad terms like '改写', 'adapt', and 'repurpose' that can match many ordinary editing or writing tasks outside this skill’s narrow intended scope. This can cause the agent to invoke the skill in the wrong context, increasing the chance of unintended file access, content transformation, or bypass of more appropriate review workflows.

Static analysis

No suspicious patterns detected.