ClawHub
Back to skill

Security audit

tcms-compliance-reviewer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed pre-publication compliance reviewer that reads the draft and related private review rules, then saves a report without changing the original draft.

Install this for teams that need pre-publication compliance review of drafts. Because it can read private compliance profiles, customer-redaction rules, and internal knowledge-base material, use it only on drafts and configurations the agent is authorized to access; consider narrowing invocation phrases if accidental activation on generic review tasks would be a problem.

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
90% confidence
Finding
The trigger list includes very generic terms such as 'review', '审核', '预审', and 'fact check', which can overlap with many unrelated editorial or quality-review tasks. This can cause the skill to activate in contexts where users did not intend to load a workflow that reads drafts, private compliance profiles, and internal knowledge sources, increasing the chance of unnecessary exposure of sensitive content and unintended processing.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill states that it reads brand rules, sensitive-term lists, product public status, customer redaction rules, and knowledge-base content, but it does not clearly warn users that private compliance profiles and sensitive internal/customer information may be accessed during execution. Without upfront disclosure, users may invoke the skill without understanding the sensitivity of the data involved, leading to over-sharing, inappropriate use on restricted drafts, or accidental handling of confidential material.

Static analysis

No suspicious patterns detected.