Back to skill

Security audit

Search Web

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local web-search connector for SearXNG with disclosed local-network use and no evidence of hidden, destructive, persistent, or credential-seeking behavior.

Install this only if you intend the agent to send search queries to a local SearXNG service on localhost:8080. Confirm that port is running the expected service, and expect the agent to use the tool for broad current-information, documentation, and fact-checking requests.

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
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest describes the function as "Search the web and return results," which is a very general activation description without constraints, scope limits, or exclusion conditions. In a manifest file, this kind of broad wording can overlap with many ordinary requests and makes it unclear when the skill should activate versus other tools.

Content

No source excerpt is available for this finding.

Internal Network Request

Medium
Category
Server-Side Request Forgery
Confidence
70% confidence
Finding

Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.

Content

Scanner excerpt · tools/search_web.py (reported line 8)May include surrounding context.

python
data = json.load(sys.stdin)
    query = data.get("query","")

    r = requests.get(
        "http://localhost:8080/search",
        params={"q": query, "format": "json"},
        timeout=10

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The usage guidance says the agent should call this tool for broad needs like 'verify facts from external sources' and 'gather links for further reading,' which overlap with many ordinary tasks. The description does not provide explicit constraints or negative examples clarifying when web search should not be invoked.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.