ClawHub
Back to skill

Security audit

Init Program

Security checks for vulnerabilities and agentic risk

Overview

This skill is a project bootstrap helper that intentionally creates or updates local agent instruction files, with clear limits and confirmation requirements.

Install this only if you want an assistant to create or update project instruction files and bootstrap repository structure. Review any generated AGENTS.md or CLAUDE.md because those files can guide future agent behavior in the repo.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill's display name, description, and default prompt broadly instruct the agent to create instruction files and initialize a project without defining clear preconditions, scope limits, or required user confirmation. This can cause the skill to trigger in situations where the user did not explicitly authorize repository-wide changes, leading to unintended file creation or modification of agent-control files that influence later behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.