Back to skill

Security audit

接单可行性评审

Security checks for vulnerabilities and agentic risk

Overview

ClawScan’s verdict is benign because the reported findings do not indicate clear harmful behavior, but the review is incomplete because the bundled icon could not be fully inspected.

The overall verdict is benign, but confidence is medium and inspection was partial: 6 of 7 components were scanned, and static checks were degraded for the icon. Consider whether the required Chinese day unit suits your use, and seek a review of the icon if you need more complete assurance 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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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"

The output format mandates the Chinese day unit “天” without offering a language or locale choice.

Low
Category
Output Handling
Confidence
92% confidence
Finding

The instruction explicitly requires durations to use “天” rather than “d”, imposing a Chinese-language output element regardless of the user's preferred language. No user opt-in or functional justification for this locale restriction is provided.

Content

No source excerpt is available for this finding.