Back to skill

Security audit

行业分析·行业机会

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward industry-opportunity research writer that creates a markdown report and updates local pipeline state for the requested industry.

Before installing, expect the skill to perform web searches and to create or modify local files under output/{industry-slug}, including session.json. Review generated policy and market claims for source quality, especially when reports are sparse and the skill falls back to general knowledge.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill allows '独立召唤' as a use condition without defining strict trigger boundaries or requiring explicit user confirmation. In an agentic environment, vague activation criteria can cause the skill to run outside the intended pipeline and perform web lookups, file writes, and session mutation on loosely related prompts, creating unintended side effects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to create 04-opportunity.md and update session.json, but it does not require notifying the user that local files will be written or modified. This can lead to silent persistence and modification of workspace state, which is risky in agent systems because the user may expect analysis only, not filesystem changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The standalone mode says a minimal session.json will be auto-generated when missing, but it omits any warning or consent requirement for creating new local state. Auto-generating session files increases the risk of unexpected artifact creation, confusing provenance, and accidental contamination of a user's workspace or downstream pipeline.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown reference mandates a single language for the skill content without offering user opt-in or documenting a justified locale restriction, which can conflict with organizational language-choice expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.