ClawHub
Back to skill

Security audit

Seasonal And Moment Marketing

Security checks across malware telemetry and agentic risk

Overview

This skill is a seasonal marketing planning guide with clear boundaries and no hidden code, installs, or credential use.

Before installing, be aware that the skill may use brand and audience context and may feed planned content into scheduling workflows. That behavior is expected for this purpose, but users should still review scheduled public posts and re-check time-sensitive dates before publishing.

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
91% confidence
Finding
The eval trigger "Help me plan my seasonal content for the year" is broad and overlaps with ordinary planning requests that could plausibly be routed to multiple adjacent skills such as content-calendar, campaign planning, or general marketing strategy. Overbroad activation criteria can cause the wrong skill to engage, increasing the chance of scope confusion, poor routing, and actions taken without the tighter authenticity and fit checks this skill is supposed to enforce.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The input "Make me a holiday content plan" is underspecified and can match a wide range of normal requests, from simple scheduling to full campaign design, without clearly constraining activation to this skill's distinct scope. This ambiguity can lead to misfires where the skill activates on generic content requests and bypasses clearer routing boundaries between planning, scheduling, and campaign execution.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.