ClawHub
Back to skill

Security audit

Daily Report Public

Security checks across malware telemetry and agentic risk

Overview

This appears to be a low-risk daily report skill, but users should know it may read local memory/project notes and update memory files.

Install this if you want daily summaries backed by local memory/project notes. Use care on sensitive projects: ask for a preview before saving, and review any memory-file updates so inaccurate summaries do not become future context.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger phrases are broad enough to match ordinary conversational requests about progress or status, which can cause the skill to activate when the user did not explicitly intend to generate a structured daily report. This raises the risk of unintended access to memory files and project files, especially because the skill's workflow includes reading multiple local data sources.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to update memory files, but it does not require user consent or notify the user that persistent project data may be modified. This can lead to silent writes, inaccurate records, or contamination of shared/project memory from a simple reporting request that the user may expect to be read-only.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.