Back to skill

Security audit

Kuaishou video

Security checks for vulnerabilities and agentic risk

Overview

The skill performs its advertised publishing and commenting tasks, with disclosed account access and manageable temporary-file risks.

Confirm the creator account, video, text, and visibility before invoking commands: they submit directly. Supply a title hint for comments to avoid targeting the wrong work. Avoid simultaneous runs because inputs share fixed temporary filenames, and remove leftover configs or screenshots when sensitive. Ego Lite itself was outside this artifact review.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk only invokes npm test; it contains no visible login check, browser interaction, video upload, publication verification, or creator comment operation. Nothing supplied establishes that this test command supports the declared workflow. The underlying test script is unavailable, so its additional behavior cannot be determined.

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 83)May include surrounding context.

md
创作者表单没有 wujie,所以上传、描述、点击发布由 `publish.js` 做完。Agent 不要另写一套填表脚本,除非脚本报了 flow error 并留下 `spaceId`。

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 111)May include surrounding context.

md
`publish.js` / `comment.js` 报错后,JSON 里的 `spaceId` 可以回到原 space。不要为了排查再开一个 space。

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 111)May include surrounding context.

md
`publish.js` / `comment.js` 报错后,JSON 里的 `spaceId` 可以回到原 space。不要为了排查再开一个 space。