Back to skill

Security audit

Sentiment Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed public-sentiment reporting workflow that searches public web sources and writes a local HTML report, with no bundled code, installs, persistence, or private-data access.

Installers should understand that this skill will search public web content and save an HTML report when used. For ambiguous requests, confirm the target, time range, and whether the user wants a generated report before invoking it; adjust the report language if the user does not want Chinese-locale HTML defaults.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest advertises trigger keywords such as "sentiment," "public opinion," and especially "reputation," which are broad phrases that can appear in many general-purpose user requests. Although examples are provided, the file does not clearly constrain activation boundaries or provide exclusion conditions, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation criteria are broad enough to match generic requests about public opinion, reputation, or media coverage without requiring explicit user intent to perform web collection and create an HTML report. This can cause unintended tool use, scope creep, and collection/processing of third-party content when the user may have wanted only a brief discussion or advice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The HTML template hard-codes lang="zh-CN" and Chinese-oriented font choices, which imposes a specific locale regardless of the user's language preference. The file does not offer a language choice or justify the locale restriction as region-specific behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.