Back to skill

Security audit

story-short-scan:短篇网文扫榜

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners found a mismatch between its advertised popularity research and reported catalog retrieval, while inspection of some scripts was incomplete.

Consider the mismatch between the advertised trend research and the reported authenticated catalog access before installing. The scan is incomplete, so it does not establish that the partially inspected scripts are safe; install only if the described behavior and required access fit your needs.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

Collecting book metadata can support the declared scanning workflow, and a single script need not cover every named platform. However, this chunk explicitly acknowledges that its source lacks popularity metrics and only retrieves catalog entries. Its numbered output reflects list position, not demonstrated popularity. The authenticated administrative catalog is therefore materially different from the advertised hot-ranking data source. Token handling supports those API calls; the supplied code does not show unrelated credential exfiltration.

Content

No source excerpt is available for this finding.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
3. 聚合:`node scripts/aggregate-rank.js {输出目录} --out {输出目录}/扫榜聚合.md --sparse 10 --scale short`。**主会话只读这份聚合**,需要原始简介与人设信息时再抽样:`node scripts/aggregate-rank.js {输出目录

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.