Back to skill

Security audit

rednote-creator

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: the scanners report no AIG findings and one concern about sending a cover prompt based on user content to an image-generation service.

The verdict is benign, not risk-free. Before installing, consider whether you are comfortable with content-derived cover prompts being sent to an external image-generation service. Confidence is medium, and the scan was partial because one local reference could not be resolved.

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 (1)

The cover-generation workflow sends a content-derived prompt to an image-generation API without disclosing this data transfer to the user.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow instructs the agent to design a cover description from the user's content and invoke autoglm-generate-image-seedream. It warns about originality certification but does not explain that the cover prompt, potentially containing personal details from the user's story, is sent to an external service.

Content

No source excerpt is available for this finding.