Security audit

Eternal Free Search (DuckDuckGo)

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward DuckDuckGo search helper that sends search terms to an external search service, which fits its stated purpose.

Install only if you are comfortable with your search queries being sent to DuckDuckGo through the ddgs client. Avoid using it for sensitive private data, credentials, or confidential business details in search terms.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is extremely broad ('use when you need to search the web for any information' and 'triggers on any web search need'), which can cause the agent to invoke this skill for a wide range of ordinary prompts. Over-broad triggering increases the chance of unnecessary external data access, prompt-routing mistakes, and exposure to untrusted web content when a simpler or safer local response would suffice.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This code sends the user's query to DuckDuckGo via the ddgs client, which is a network operation that transmits user-provided data off-system. The file contains no confirmation prompt, user-facing warning, logging disclosure, or explanatory comment/docstring that makes this transmission explicit to the user.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The news search function makes an outbound request containing the user's query and contextual parameters such as region and time filter. Although network access is central to search functionality, this file does not provide any user-facing notice that entered queries are being sent to an external service.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The answers lookup sends the provided query to an external service through the ddgs client. There is no visible warning, confirmation, or explanatory comment informing users that their input leaves the local environment.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This function performs a network search for images using the user-supplied query, which transmits potentially sensitive search terms to a third party. The file lacks any user-facing disclosure that this external transmission occurs.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The suggestions mode submits the user's query fragment to an external service to retrieve completions. No prompt, status message, or inline documentation warns that partial input is transmitted off-device.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The options table sets --region default to wt-wt and presents other locale-specific codes, but the skill does not explain how locale is chosen or offer an explicit user-facing opt-in for region selection. This may violate language/locale policy expectations when a skill implicitly applies a locale preference.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.