Security audit

行业分析·数字化方案

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent industry research workflow that writes an analysis file and pipeline state, with no evidence of hidden execution, credential access, exfiltration, or system persistence.

Install this if you want an agent to generate and maintain an industry digital-solutions analysis. Expect it to create or update files under the relevant `output/{industry-slug}` directory and to use current public vendor research; review generated claims and sources before relying on them.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly writes 03-digital-solutions.md and updates session.json, but the visible description and operational contract do not prominently warn that filesystem state will be created or modified. In agent environments, silent file writes can surprise callers, break assumptions about read-only analysis, and enable unintended overwrites of user data or pipeline state when invoked in the wrong context.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: Standalone mode states that it will automatically generate a minimal session.json when none is provided, but does so without an explicit safety warning. Automatic file creation increases risk because an apparently analytical skill can mutate the workspace unexpectedly, create misleading state for later pipeline stages, or write into unintended directories if path handling is weak elsewhere in the system.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown file contains only Chinese-language instructions and examples, which can amount to an implicit language constraint for users of the skill. Under the policy, language restrictions should either be optional for the user or clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.