ClawHub
Back to skill

Security audit

Clawaudit

Security checks for vulnerabilities and agentic risk

Overview

This is a minimal placeholder repo-auditing skill with no executable behavior, persistence, credential use, or hidden data handling.

Only use this skill with repositories you own or have permission to audit. The current artifact is mostly a placeholder and does not provide a working scanner, so review future versions again before relying on or granting broader access.

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
87% confidence
Finding

The skill explicitly encourages users to manually add any repository they care about, without defining authorization checks, ownership validation, or scope restrictions. In a security-auditing context, broad instructions to target arbitrary repositories can enable unauthorized scanning of third-party codebases or misuse of the skill for reconnaissance, making the lack of constraints materially risky.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.