Back to skill

Security audit

Jys

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: the scanners report no AIG findings and mostly clear security checks, while flagging a possible instruction to copy reference scripts and evade plagiarism detection.

The verdict is benign, but treat it as a medium-confidence assessment rather than a guarantee of safety: Skillspector coverage was partial. Before installing, consider whether you are comfortable with the reported copying and similarity-evasion guidance, which could create copyright or platform-policy problems.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Benign adaptation framing conceals instructions to copy source material and evade plagiarism detection.

Medium
Category
Prompt Injection
Confidence
98% confidence
Finding

The skill explicitly directs the agent to copy the substance and attention-grabbing elements of reference scripts while reducing similarity to avoid plagiarism detection. This is deliberate concealment rather than ordinary adaptation guidance; in a commercial scriptwriting workflow, it can facilitate unauthorized copying and expose users to intellectual-property claims and platform penalties.

Content

No source excerpt is available for this finding.

L23 mandates Beijing time for timestamps and naming without user opt-in or a documented regional justification.

Low
Category
Output Handling
Confidence
94% confidence
Finding

The template explicitly specifies Beijing time rather than following the user's timezone or offering a locale choice. No region-specific purpose is documented to justify imposing this timezone.

Content

No source excerpt is available for this finding.