ClawHub
Back to skill

Security audit

Context Archive Skill

Security checks across malware telemetry and agentic risk

Overview

This skill coherently provides user-triggered conversation archiving to local Markdown files, with no hidden execution or external data transfer found.

Install only if you are comfortable with selected conversation summaries being saved as persistent files in the workspace. Avoid archiving secrets, credentials, personal data, or proprietary details unless you intend to retain them, and review or delete old files in archives/ as needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README describes archiving and later recall, but it does not clearly warn users that conversation contents are persisted as markdown files on disk. Because conversations can contain secrets, personal data, or proprietary material, users may reasonably trigger archiving without understanding that sensitive context will remain stored in the workspace and may be accessible later to tools, other agents, or anyone with filesystem access.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation states that conversations are archived to local Markdown files under archives/, but it does not clearly warn users that potentially sensitive conversation content will be persisted on disk beyond the current session. This can lead to unintended retention of secrets, personal data, or proprietary information, especially in shared workspaces or synced directories where users may assume the feature is ephemeral.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly writes conversation-derived summaries to persistent files under `archives/`, but the user-facing behavior does not provide a clear upfront warning about data persistence, sensitivity, or retention implications at the point of use. This can cause users to unknowingly store confidential or personal information in the workspace, where it may later be read, indexed, or committed to version control.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
Mandating a Chinese-first interface without user opt-in can cause users to misunderstand consent, file-writing behavior, or recall operations if they are not comfortable reading Chinese. In a skill that stores persistent summaries, reduced comprehension increases the chance of accidental data handling decisions rather than direct compromise.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.