Security audit

Bright Data

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent Bright Data wrapper for web search and webpage scraping, with privacy and acceptable-use considerations but no hidden or destructive behavior found.

Install only if you intend to use Bright Data for scraping or search. Use a scoped API key and zone, monitor usage and costs, avoid sensitive, internal, tokenized, or credentialed URLs and confidential queries, and confirm that your scraping complies with applicable law and target-site rules.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill invokes shell scripts (`bash scripts/search.sh` and `bash scripts/scrape.sh`) but does not declare permissions, creating a mismatch between documented capabilities and the trust signals exposed to users or reviewers. Hidden or undeclared execution capability increases the chance of unintended command execution pathways and makes risk evaluation harder.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The description advertises scraping of "any webpage" and search in broad terms, which can cause the skill to trigger on many ordinary browsing or research requests without clear user intent. Overbroad activation scope is dangerous because it can route user queries and target URLs to an external scraping provider unexpectedly.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The scraping usage section explains how to scrape a URL but does not define when the skill should or should not be used, leaving activation boundaries ambiguous. This can lead to unnecessary third-party transmission of URLs and page contents, especially in environments where multiple skills may compete for generic web tasks.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill description omits a warning that user-requested URLs and retrieved page data are sent to a third-party scraping service. This is a privacy and data-handling risk because users may provide sensitive, internal, or authenticated URLs without realizing the destination and processing path.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The setup instructions request an API key and zone name but do not include guidance on secure secret handling, storage, or rotation. In practice this increases the likelihood of credential exposure through shell history, logs, screenshots, or insecure environment configuration.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.