ClawHub

Chat Lift

Security checks across malware telemetry and agentic risk

Overview

ChatLift is a coherent local chat-export archiver, but users should treat its generated archives as sensitive private files.

Install only if you are comfortable creating a durable local copy of your AI conversations. Store the archive in a private directory, avoid cloud-synced/public/web-served folders unless you intend to share it, and review or redact sensitive chats before importing or publishing generated HTML/JSON/Markdown files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README instructs users to import and archive highly sensitive AI conversation exports, but the quick-start workflow does not prominently warn that these exports may contain secrets, personal data, tokens, internal prompts, or regulated information. Because the tool writes this content into searchable local markdown/HTML/JSON archives, users may unintentionally broaden exposure through local indexing, backups, file sharing, or accidental publication.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This section promotes importing and archiving AI conversations without a prominent warning that those exports may contain API keys, personal data, credentials, business secrets, or regulated information. Because the tool indexes and stores that content locally, users may unintentionally create a concentrated searchable repository of sensitive data.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The HTML archive is described as static, searchable, and easy to open, but there is no explicit warning that the generated web files expose the full contents of conversations to anyone with filesystem or hosting access. Users could place the archive in synced folders, shared drives, or publish it accidentally, causing broad disclosure of private conversations.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The code generates a full static HTML archive of all loaded conversations and writes it to disk without any consent prompt, warning, or guardrail about the sensitivity of the exported content. Since AI chats often contain secrets, personal data, or proprietary material, silently exporting them into browseable files increases the risk of unintended local disclosure, backup leakage, sharing, or publication.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal