ClawHub
Back to skill

Security audit

Bug Fix Protocol

Security checks for vulnerabilities and agentic risk

Overview

This is a benign debugging checklist that tells agents to reproduce bugs with tests, make minimal code and test changes, and document the fix.

Install this if you want an agent to follow a strict test-first bug-fixing process. Be aware that most instructions are in Russian, and that using the skill during debugging will normally involve reading related code, adding or updating tests, changing bug-related code, running tests, and documenting the fix.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The README presents the skill entirely in Russian, including its title/description and usage guidance, with no indication that users may choose another language. This can violate language/locale policy when a skill forces a specific language without user opt-in.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding
Suspicious Unicode normalization or mixed-script content

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The manifest metadata at L003-L004 is in English, but the substantive operational instructions from L014 onward are written in Russian and presented as mandatory protocol text. This creates a language/locale policy concern because the skill effectively requires Russian comprehension without opt-in, alternative language support, or any stated region-specific justification.

Static analysis

No suspicious patterns detected.