ClawHub
Back to skill

Security audit

Spotlight

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward macOS Spotlight search helper that limits searches to user-specified directories and explicitly warns against reading files or using sudo without consent.

Install only if you want an agent to use macOS Spotlight for local file discovery. Use narrow directories for searches, review the returned paths before allowing file reads, and do not approve privileged indexing commands unless you intentionally run them yourself in Terminal.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

mdutil -s /path/to/volume

text

⚠️ **WARNING**: Do NOT execute any `sudo` commands from this skill without explicit user confirmation. Commands like `sudo mdutil -i on` require admin privileges and should only be run by the user directly in Terminal.

## Integration with LLM Workflows

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
### ⚠️ Security Note

- **Never automatically read files** - always ask for user confirmation first
- **Never execute sudo commands** - only show them as information
- **Respect user privacy** - don't search directories user hasn't specified

## Advanced Query Syntax

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This shell script includes user-facing natural language in Chinese comments and English usage/output text, but does not indicate any language preference or opt-in. The policy category specifically calls for flagging language or locale constraints when the skill effectively forces a language without user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.