Back to skill

Security audit

wechat-viral-topic

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: it found one low-severity concern about broad activation triggers, while the other assessed areas were rated OK.

The verdict is benign, but benign does not mean risk-free and confidence is medium. Consider whether the broad triggers may cause unwanted activation. The scan was partial: it did not analyze binary content and could not resolve several local path references, so evidence is incomplete.

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
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 (1)

Standalone triggers such as "headline" and "hot take" are overly broad and can activate the skill outside topic-selection workflows.

Low
Category
Trigger Abuse
Confidence
91% confidence
Finding

The trigger list includes common terms that can appear in requests to explain or discuss existing headlines and opinions, rather than develop content topics. Although the description establishes a content-planning purpose, it does not explicitly restrict these triggers to that intent or provide exclusions.

Content

No source excerpt is available for this finding.