Back to skill

Security audit

Baidu Image Classify

Security checks for vulnerabilities and agentic risk

Overview

This Baidu image-recognition skill is coherent, but it needs Review because it can fetch arbitrary URLs and send image data to Baidu while handling API credentials unsafely.

Install only if you are comfortable sending images to Baidu Cloud and can revise the examples before use. Credentials should be moved to protected configuration, tokens should not be placed in URLs where avoidable, and remote URL inputs should be restricted to validated public HTTPS image URLs with timeouts, size limits, and content checks.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:41
Finding

Hard-Coded API Credential and Unsafe OAuth Token Transmission

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:55
Finding

Unrestricted User-Controlled URL Fetch Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

At L005 the document states the skill is complete and callable, but the primary code example still uses SECRET_KEY = "需要补充" at L042, which means authentication cannot work as written. Later examples also rely on get_access_token() and encode_image() at L099-L102 and L144-L145 without defining them anywhere in the file, reinforcing that the implementation is not actually ready as claimed.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill accepts local images or image URLs and transmits the image contents to Baidu Cloud for processing, but the documentation does not clearly disclose this data transfer to users. This is dangerous because users may unknowingly submit sensitive personal, commercial, or internal images to a third-party service, creating privacy, compliance, and data-handling risks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

整份技能文档及面向用户的话术均默认且仅使用中文,例如“现在你可以”“直接吩咐”等,没有说明该技能仅面向中文用户,也未提供语言选择。根据该规则,未经过用户选择而强制单一语言/locale 可能构成自然语言政策问题。

Content

No source excerpt is available for this finding.