Back to skill

Security audit

Laravel Package Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Laravel package recommendation helper with disclosed package-search behavior and no evidence of hidden, destructive, or credential-seeking activity.

Before installing, understand that a working implementation may contact Packagist/GitHub and may cache package-search results locally. Also verify whether the package includes the referenced search script, because this artifact does not contain it.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly performs live network access and creates a local cache file, but the specification does not require notifying the user or obtaining consent before those side effects occur. In agent environments, silent external requests and filesystem writes can expose user queries to third parties and create unexpected persistence on disk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation list contains phrases like "Laravel package for XXX" and "帮我评估这个包" that could match a wide range of normal conversation and do not clearly define when this skill should activate versus when other Laravel or package-analysis skills should handle the request. The file also does not provide negative examples or scope constraints to reduce accidental invocation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 265)May include surrounding context.

md
## 10. Data Sources

- **Packagist API**: `https://packagist.org/api/search.json?q=`
- **GitHub API**: `https://api.github.com/repos/{vendor}/{package}`
- **GitHub Trending**: Community activity
- **Official Laravel Packages**: laravel.com/packages

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L03 instructs users to run a command for live rankings with real-time Packagist data, yet this file itself contains fixed package rankings and dated metadata rather than dynamically generated results. This is an active documentation contradiction because it presents the file as reflecting live data while the actual artifact is static reference content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file presents its instructions and usage guidance primarily in Chinese, including the operational note at the end, without stating that the skill is intended only for Chinese-speaking users or offering an alternative language. That creates a natural-language locale constraint without user opt-in, which falls under the policy check for language or locale violations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The final note is written entirely in Chinese, while the rest of the document is in English. This imposes a language shift without user opt-in and no indication that the file is intentionally region-specific, which fits the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.