Back to skill

Security audit

延期原因归因

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this skill as benign with medium confidence: the reported findings are limited to an incomplete review of an image and a test that conflicts with the declared trigger scope, while most other checks completed without reported issues.

The verdict is benign, but confidence is medium and Skillspector analysis is partial: 6 of 7 components were scanned, and the image was not fully interpretable. Consider whether that coverage and the trigger-scope mismatch are acceptable before installing.

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 (2)

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 10)May include surrounding context.

md
icon: "assets/icon.png"

TC005 expects the skill not to trigger for a remediation question explicitly included in the manifest.

Low
Category
Excessive Agency
Confidence
96% confidence
Finding

The manifest explicitly includes “还能不能补救” as a trigger, but TC005 supplies “这单还能补救吗” and expects trigger_skill=false with no tool calls. This test encodes a routing expectation contrary to the declared scope, although it does not establish how the runtime currently behaves.

Content

No source excerpt is available for this finding.