ClawHub
Back to skill

Security audit

Trend Spotter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed marketing trend-analysis workflow with limited local memory use and no evidence of hidden execution, exfiltration, or destructive behavior.

Install this if you want a marketing trend-report assistant. Review its memory behavior first: it can save trend reports and durable trend notes, and its broad trigger wording may make it run for some general campaign-timing or content-theme requests.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description uses expansive trigger phrasing like 'what trends should my brand jump on' and 'time a campaign around a cultural moment,' which overlaps with common marketing strategy requests and increases the chance of unintended invocation. In an agent ecosystem, overly broad routing language can misclassify user intent, causing the wrong skill to run and propagate misleading outputs or unnecessary memory writes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The auto-activation rule is broad enough to match generic requests such as 'what to post around' or 'when to act,' which can cause the skill to trigger in situations where another skill or normal conversation handling would be more appropriate. This creates a scope-selection vulnerability: the agent may invoke a trend-analysis workflow, write to memory, and steer downstream handoffs without sufficiently specific user intent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The template directs the skill to recommend 'Influencer type' and includes action items like briefing creators, which expands behavior into influencer-selection/briefing despite the manifest explicitly saying creator-finding belongs to another skill. This can cause scope bleed, unsafe agent routing, and decisions being made without the controls or expertise expected in the dedicated influencer-discovery workflow.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The 'Next Steps' section tells the user to 'Create content calendar incorporating [cultural moments],' which conflicts with the manifest's statement that post-calendar building belongs to another skill. This is dangerous because downstream agents or users may rely on this skill for calendar construction, bypassing intended separation of responsibilities and any specialized safeguards in the calendar-building skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.