ClawHub
Back to skill

Security audit

SDD Global Init

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, manually triggered workspace documentation initializer with proportionate file creation and scanning behavior.

Install only if you want Chinese SDD documentation generated for a chosen workspace. Review the generated outline before confirming, and choose a workspace that does not contain unrelated sensitive files because the skill scans project metadata and may use diagram prompts with the image-generation skill.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The rules explicitly require all user-facing information and all generated global documents to be written in Chinese, and image text to be Chinese except for technical terms. This forces a specific language/locale choice rather than offering the user an option, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.