ClawHub
Back to skill

Security audit

Supercoder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent coding workflow that edits project files and runs tests only as part of an expected user-directed implementation process.

Install this only if you want an agent to make code changes and run repository-defined tests as part of feature delivery. Review the design checkpoint carefully before proceeding, especially in repositories with risky test scripts or sensitive build steps.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The phase explicitly instructs the agent to implement changes with Edit/Write tools and run tests with Bash, but it does not require a warning or confirmation that project files may be modified and shell commands may be executed. In a code-implementation skill, this omission can lead to users triggering state-changing actions or command execution without clear informed consent, increasing the risk of unintended file changes or execution of unsafe test/build scripts from the repository.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.