Back to skill

Security audit

Ego WeChat Official Account Draft

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because a scanner found a mismatch between its stated article-drafting purpose and the behavior it could verify; the scan was partial, so the evidence is incomplete.

Review the skill's declared purpose and permissions before installing. The scan found concerns about a purpose mismatch, possible loss of unsaved edits, and undisclosed screenshots on disk; because coverage was partial and the test script's contents were unavailable, the evidence does not establish the full behavior.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The supplied code contains only npm test; it shows no Ego Lite interaction, login or account validation, consent gating, or draft-saving action. Its visible purpose therefore differs materially from the description. Any additional behavior of the test script cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

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.

The clear-unload operation silently disables the page's navigation-away warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The clear-unload operation unconditionally removes the page's onbeforeunload handler without checking for unsaved changes. Subsequent navigation or closure can therefore discard pending edits without the editor's normal warning, undermining data preservation in a draft-editing workflow.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
75% confidence
Finding

Overly Broad Trigger: description clause 'Use when the user asks for a 公众号文章草稿, 图文草稿, or mp' activates on 'a', a common word that will activate in many unintended contexts

Content

No source excerpt is available for this finding.

Page screenshots are written to disk without disclosure of the file-writing behavior.

Low
Category
Output Handling
Confidence
87% confidence
Finding

captureViews writes three screenshots to the supplied directory, potentially persisting editor content. The provided file contains no confirmation, user-facing log, or explanatory comment documenting these writes.

Content

No source excerpt is available for this finding.