ClawHub
Back to skill

Security audit

Sharpagent Intelligence Monitor

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill monitors public tech sources and creates briefings; its web fetching and local archiving are expected for that purpose but should be managed deliberately.

Install this if you want an agent to fetch public AI and tech information and produce recurring briefings. Before use, decide where archived briefings and any ontology records should live, how long to keep them, and whether the referenced fetch scripts are available and trusted in your environment. Verify important business or competitive claims independently rather than relying only on the skill's scoring labels.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (1)

Missing User Warnings

Low
Confidence
91% confidence
Finding
The skill explicitly archives generated briefings to a local path, but the user-facing description and workflow do not warn that gathered content may be written to disk automatically. This can create unexpected persistence of potentially sensitive monitoring topics, queries, or derived summaries, especially in shared or regulated environments.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.