Cross Bot Communication

• Outcome: Review
• Latest audit: May 29, 2026, 9:24 PM
• Version:
  1.0.3

Overview

This skill is not clearly malicious, but it should be reviewed because it automatically maps Telegram group/channel relationships and can relay messages without clear user controls.

Review before installing. Use a dedicated low-privilege Telegram bot token, restrict scans to specific groups/channels you approve, require a visible preview and confirmation before messages are sent, and ensure any relationship table can be reviewed and deleted. Avoid granting admin rights unless necessary.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README explicitly describes automatic scanning of existing groups/channels and construction of a relationship table, but does not disclose privacy implications, consent expectations, retention, or access controls for the collected social-graph data. In a messaging/agent context, silently enumerating memberships and persisting owner/bot/group mappings can expose sensitive relationship metadata and create unauthorized surveillance concerns.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: Presenting the skill as 'zero-configuration' and 'automatic' downplays that it may auto-bind identities and persist relationship data derived from user/group context. That framing increases the chance that operators enable behavior without understanding that social-context metadata is being inferred and stored, which can lead to privacy violations or unexpected state changes.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly describes automatic scanning of existing groups and channels to build a social relationship map, but it provides no user-facing notice, consent step, scope limitation, or retention policy. In an agent context, this can expose membership and relationship metadata without informed user approval, creating privacy and data-minimization risks.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill describes sending messages to a target bot through subagents but does not warn that user content or metadata may be transmitted to third-party bots or channels. This creates a real outbound disclosure risk because users may not realize their requests are being relayed externally, potentially exposing sensitive information or identities.

VirusTotal

65/65 vendors flagged this skill as clean.