ClawHub
Back to skill

Security audit

Kinema's Concept Re-Search

Security checks across malware telemetry and agentic risk

Overview

This skill is a research helper that searches the web and saves research materials locally, and the reviewed artifacts disclose behavior that fits that purpose.

Install only if you want an agent to perform web-based concept research and save local research projects. For vague prompts, ask the agent to confirm before cloning repositories or downloading PDFs, and review downloaded third-party content before executing anything from it.

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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The documented trigger phrases are generic, everyday queries such as asking whether anyone has done something or to research a topic. In agents that auto-route skills from conversational text, overly broad triggers can cause unintended invocation of this skill, leading to unnecessary external searches, project creation, or follow-on actions the user did not explicitly consent to.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README describes an output structure that includes cloned repositories and downloaded papers, but it does not clearly warn users that the skill may perform network retrieval and write potentially large amounts of data to disk. If invoked unexpectedly or by a loosely matched trigger, this can consume bandwidth, storage, and expose the environment to unreviewed third-party content.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger text is broad enough that the skill may activate for vague requests like 'research xxx' or 'check the status of xxx' without clear user intent or boundaries. In context, that can lead to unintended web searching, local cloning, and file downloads based on an ambiguous request, expanding the chance of unsafe or privacy-impacting actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow explicitly instructs the agent to clone GitHub repositories locally and download PDFs/papers, but the skill description does not warn users that external content will be fetched and stored on disk. That omission is dangerous because users may unknowingly trigger exposure to untrusted content, excessive disk/network use, and possible downstream risks from processing attacker-controlled repositories or documents.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.