Security audit

Deep Research

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown research-process skill with no executable code, install hooks, credential handling, network automation, or hidden persistence.

Installers should expect a Chinese-language deep-research framework. Review any generated action items before allowing changes such as creating skills, trying tools, or updating memory files, but the inspected artifact does not itself perform those actions.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The substantive skill instructions and templates are written entirely in Chinese, which effectively imposes a specific language/locale on use of the skill. There is no indication that the user may choose another language, nor any documented reason that the skill is region- or locale-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.