Security audit

super-search-engine

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only search helper that points agents at public search engines, with some privacy and safety caveats users should understand.

Install only if you want a search-URL reference skill that may send queries to both China-region and global search providers. Avoid using the reduced-safety, exposed-password, or sensitive-query examples unless you have a legitimate reason and understand the privacy and content risks.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (6)

Ae1

High

Category: analysis-evasion
Content: - `references/international-search.md` - International search guide
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: This markdown file presents the skill’s key description, features, changelog, and usage sections in Chinese only. The policy explicitly calls for flagging language or locale constraints when the skill forces a specific language without user opt-in, and no alternative language option or justification is provided here.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: This manifest/config file embeds multiple China-specific search engines and CN-targeted Bing endpoints as fixed options, with region values set to "cn". Because the file provides no natural-language justification or user opt-in for this locale targeting, it creates a locale-policy concern under the rule for forced language/region behavior.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The document explicitly provides DuckDuckGo examples using `kp=-1`, which disables safe search, but does not warn users that this may surface explicit, harmful, or otherwise unsafe content. In a reusable agent skill, such examples can normalize or automate lower-safety search behavior and may cause the agent to retrieve risky material unintentionally.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The Startpage section promotes proxy/anonymized browsing and later recommends sensitive-query workflows, but it overstates privacy properties without warning about residual risks such as destination-site logging, browser fingerprinting, ISP visibility, and legal or policy implications. Users may be misled into believing these methods provide stronger anonymity than they actually do.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The file presents all instructional content in Chinese and does not offer an alternative language or indicate that Chinese is required by context. A skill that forces a specific language without user opt-in can violate organizational language/locale policy.

Static analysis

No suspicious patterns detected.