Security audit

Project Doc Management

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward project-document management guide with disclosed file-reading and document-organization behavior, but users should confirm paths and file changes before letting an agent modify documents.

Install only if you want an agent to organize and read documents in the configured ProductManagement folder. Set PM_PATH narrowly, review any proposed 项目概览.md changes, and approve file moves or directory creation before execution.

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

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
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 states that when product-line documents undergo major updates, the agent 'must' synchronously update 项目概览.md, but it does not require explicit user confirmation or warn that this changes user files. In an agent setting, mandatory write behavior against user documentation can cause unauthorized or surprising file modification, especially if the model infers that an update is 'major' without clear approval.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The migration section provides shell commands that create directories and move files into the configured path, but it lacks warnings about overwriting, misconfigured paths, or the need for confirmation before moving user content. In an automated skill context, examples like mv can normalize destructive filesystem operations and lead to data loss or unintended relocation of files if the agent applies them directly.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The skill documentation is entirely in Chinese and does not offer a language choice or indicate that Chinese is an optional or region-specific requirement. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.