ClawHub
Back to skill

Security audit

Timeline Digest Tool Free

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly coherent for generating a Twitter/X timeline digest, but it combines broad activation wording with authenticated timeline access and local persistence that users should review before installing.

Install only if you are comfortable letting an agent run the authenticated bird CLI to read your personalized Twitter/X timelines and store processed tweet IDs and timestamps locally. Prefer using it only for explicit timeline digest requests, not general analytics or reporting prompts.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Confidence
91% confidence
Finding
The skill claims to be 'read-only' while it explicitly creates, updates, and cleans local state files containing processed tweet IDs and timestamps. This misleading safety claim can cause users or agents to authorize execution under false assumptions, leading to unanticipated local data modification and persistence of activity metadata.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger conditions are overly broad ('data analysis, report generation, statistical insight, visualization'), which can cause the skill to activate in unrelated contexts and gain access to authenticated timeline-fetching behavior when not specifically requested. In an agent environment, overbroad activation is dangerous because it may lead to unnecessary use of exec-capable tooling and authenticated data access beyond the user's intent.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs use of an authenticated third-party CLI ('bird') with cookie-based login and also writes local state, but it does not clearly warn users that running it accesses account-scoped timeline data and persists metadata locally. In this context, the combination of exec permission, authenticated session use, and insufficient disclosure raises the risk of privacy violations, unintended account-data access, and unsafe operator trust.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.