Security audit

China company search fengniao

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Riskbird/Fengniao company lookup skill that discloses its external API use and shared public key, with privacy caveats for business queries.

Install only if you are comfortable sending company names, person names used for company lookup, entids, and due-diligence query details to Riskbird/Fengniao. Use your own FN_API_KEY if you need account control or paid quota; the built-in key is shared and quota-limited.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (6)

Context-Inappropriate Capability

Medium

Confidence: 99% confidence
Finding: The file contains a hard-coded shared API key that is automatically used when no user-supplied key is present. Embedding a credential in distributed client-side or skill code exposes it to anyone who can inspect the package, enabling unauthorized reuse, quota exhaustion, account abuse, and possible attribution of malicious activity to the publisher's account.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill is configured with auto_invoke and includes very broad enterprise-query examples such as generic due diligence, supplier verification, and company/person lookup requests. In practice this can cause the agent to trigger the skill for vague prompts and send company names or personal names to an external service without a sufficiently explicit user decision, increasing privacy and consent risk.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The documentation states that requests are sent to an external service using URL query parameters including apikey and channel, but it does not clearly warn users that their queried company names or personal names will be transmitted off-platform. Using URL parameters for sensitive credentials and lookup data can increase exposure through logs, proxies, browser history, or intermediary systems, making this more dangerous than a normal undocumented third-party call.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The code appends the API key to the request URL via query parameters. Query strings are commonly logged by proxies, servers, browser/network tooling, and observability systems, which increases the chance of credential disclosure even when HTTPS is used. In a company-search skill that makes external API calls, exposing a reusable API credential can enable unauthorized API usage and billing abuse.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The call function transmits caller-supplied parameters to an external service without any user-facing notice, consent, or data-minimization guardrails in this file. Because this skill is used for enterprise due diligence and risk lookup, callers may provide sensitive company or personal data; silent transmission to a third-party API creates privacy, compliance, and data-governance risk.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: Several aliases in this range are generic everyday business terms such as supplier-, contract-, boss-, and interview-related phrases that can plausibly appear in normal conversation without an explicit request to invoke a company-risk lookup skill. This increases the chance of accidental or over-broad routing, which could trigger unintended enterprise background checks and expose external data lookups or sensitive business profiling in contexts where the user did not clearly ask for them.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.