ClawHub
Back to skill

Security audit

Line Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only repository audit checklist that is broadly triggered but does not show hidden, destructive, persistent, or exfiltrating behavior.

Install this when you want a structured repository health audit. Expect it to read broadly across the repo and possibly run relevant local diagnostic commands if the matching tooling exists; ask for a narrower audit if you do not want full-repo inspection.

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
96% confidence
Finding

The skill description is broadly phrased to trigger on generic repository-help requests such as auditing, assessing project health, and deciding what to work on next. This can cause the skill to activate in many contexts where narrower or more specialized skills should be used, increasing the chance of over-collection, unnecessary repo-wide inspection, or incorrect execution paths driven by ambiguous intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.