Back to skill

Security audit

锋哥智能搜索

Security checks for vulnerabilities and agentic risk

Overview

This is a simple search helper that contacts Bing or DuckDuckGo as advertised, with privacy and result-labeling caveats but no hidden persistence or destructive behavior.

Install only if you are comfortable sending search queries to Bing or DuckDuckGo. Avoid using it for secrets, credentials, private project names, or sensitive personal data, and treat its official or quality labels as heuristic rather than verified trust signals.

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 (1)

T09 · Insecure Skill Coding Practices

Warning
Location
skill.py:46
Finding

Spoofable Trusted-Domain Classification

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill advertises and requires network-capable components but does not declare any explicit tool scope or permissions boundary in the manifest. This can lead to overbroad network access expectations, weak reviewability, and accidental use in environments where users or hosts are not clearly informed that external requests will occur.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation does not warn users that their search terms will be transmitted to third-party search engines, which may expose sensitive prompts, internal project names, or personal data. In agent contexts, users may reasonably assume local processing unless outbound disclosure is clearly disclosed, making this a real privacy and data-handling issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The description states that Chinese queries go to Bing and English queries go to DuckDuckGo, making language detection drive behavior automatically. This is a language/locale-based policy decision presented as default behavior without user opt-in at the point of use, which fits the natural-language policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file’s natural-language description states that Chinese searches go to Bing and English searches go to DuckDuckGo by default, and the code implements this behavior automatically. This is a language/locale-based policy choice applied without explicit user opt-in, which matches the natural-language policy violation criteria.

Content

No source excerpt is available for this finding.