Back to skill

Security audit

imagegen-batch

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this image-generation skill as benign with medium confidence: they report one language preference concern, while finding no issues in the completed AIG scan; Skillspector coverage was partial.

Consider whether the Chinese-language prompt and filename requirements suit your needs. The overall verdict is benign, but confidence is medium and the scan is incomplete: Skillspector inspected five of six components fully, partially inspected one, and its tool-misuse analysis hit a parser limit. AIG completed with no findings.

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 (3)

The skill mandates Chinese prompts and filenames without user opt-in.

Medium
Category
Output Handling
Confidence
99% confidence
Finding

L062–L068 require all image-generation prompts to be written directly in Chinese, and L128 additionally requires Chinese filename summaries. Neither requirement offers a language choice or establishes a locale-specific need; avoiding Unicode-escape errors justifies using literal text, not forcing Chinese.

Content

No source excerpt is available for this finding.

The filename rule requires Chinese scene words without offering a language choice.

Low
Category
Output Handling
Confidence
90% confidence
Finding

The changelog states that final filenames must use Chinese scene words from the beginning of each image prompt. This imposes a specific language on generated filenames without user opt-in or a documented locale-specific justification.

Content

No source excerpt is available for this finding.

Generated filename summaries are required to use Chinese without user opt-in.

Low
Category
Output Handling
Confidence
96% confidence
Finding

The filename rule explicitly requires the summary to use Chinese scene words from the start of the prompt (“摘要取 prompt 开头的中文场景词”). This imposes a specific language on generated filenames without offering a language choice or documenting a locale-specific justification.

Content

No source excerpt is available for this finding.