ClawHub

youtube-comments-api-skill

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it sends YouTube search and comment-collection requests to BrowserAct using a BrowserAct API key.

Install only if you intend to use BrowserAct for YouTube data collection. Set BROWSERACT_API_KEY through an environment variable or secret manager, avoid sensitive search terms, review BrowserAct and YouTube terms, and expect BrowserAct quota/network use when the skill runs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to access an environment variable (`BROWSERACT_API_KEY`) and invoke an external API-backed Python script, which implies secret handling and networked code execution. Because these capabilities are not explicitly declared as permissions, the trust boundary is unclear and a reviewer or runtime may underestimate what the skill can access or transmit, increasing the risk of unintended secret exposure or unreviewed outbound requests.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description uses very broad proactive triggers such as market research, sentiment analysis, competitor monitoring, and public response tracking, which can match many generic research requests not specifically asking for YouTube comment extraction. This can cause the agent to invoke the skill in contexts where the user did not intend external browsing/API use, leading to unnecessary data collection, unexpected network activity, or overreach into competitor-monitoring/surveillance-style tasks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal