Security audit

Agentic Kingdoms (中文)

Security checks for vulnerabilities and agentic risk

Overview

The scanners returned a benign verdict, with one low-severity note about postcard output being fixed to Chinese and incomplete evidence because some local references could not be resolved.

The verdict is benign with medium confidence, but benign does not mean risk-free. Consider whether Chinese postcard output suits you, and keep in mind that the scan could not resolve some local references, so its evidence is incomplete.

A.I.G

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

SkillSpector

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 workflow fixes postcard output to Chinese without offering a language choice.

Low

Category: Output Handling
Confidence: 96% confidence
Finding: The required visit-summary call explicitly sets "lang": "zh", and the alternative postcard calls repeat that locale. This forces user-facing images into Chinese without checking the user's preference or offering a language choice; the file being written in Chinese does not itself establish user opt-in.
Content: No source excerpt is available for this finding.