ClawHub
Back to skill

Security audit

requirement-pre-review

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown review checklist skill for requirement documents, with no code execution, persistence, or external data access.

Install this if you want automatic Chinese-language requirement review reports. Be aware it may activate when you paste requirement-like text, so avoid pasting sensitive PRDs unless you intend them to be reviewed in the current agent session.

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

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is configured to trigger on very broad phrases and even on any pasted requirement-like text, which can cause unintended activation and override normal tool-selection boundaries. This increases the chance that unrelated user content is routed into the skill automatically, creating prompt-routing confusion, unwanted processing of sensitive documents, and degraded user control over when the skill runs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill hard-codes Chinese-language behavior and output format without considering the user's language preference, which can cause misalignment with user intent and reduce transparency of the skill's actions. While not a direct code-execution issue, it can lead to unsafe misunderstandings in requirement reviews, especially when users provide multilingual content or expect outputs in another language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.