ClawHub
Back to skill

Security audit

genspark-ralph-loop

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed development workflow helper that edits the target project, tracks progress, and may spawn Genspark child sessions, with no evidence of deception, exfiltration, or unsafe persistence.

Install only for projects where you are comfortable letting an agent modify code, PRD checkboxes, and `.ralph-claw/` tracking files, run local verification commands, and optionally spawn Genspark child sessions. Review its changes before committing, pushing, deploying, or using it on sensitive repositories.

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 (3)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
All user-facing guidance in the README is written only in Korean, and the document does not indicate that another language can be used or that Korean is required for a justified regional purpose. This can violate language/locale policy when a skill imposes a specific language without user opt-in.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The manifest description and the entire skill guidance are written in Korean, and there is no statement that the skill should adapt to the user's preferred language or offer a locale choice. This creates a natural-language locale policy concern because the skill effectively constrains interaction to a specific language without user opt-in or documented justification.

Missing User Warnings

Low
Confidence
87% confidence
Finding
This markdown file states that the skill records status under `.ralph-claw/` and updates progress information, which affects files in the user's project. While the behavior is described, there is no explicit caution or warning to the user that running the skill will create and modify files in the workspace.

Static analysis

No suspicious patterns detected.