Security audit

Call Deepseek V3 Llm

Security checks for vulnerabilities and agentic risk

Overview

The skill is advertised as a DeepSeek V3 caller, but its actual instructions are an unrelated role-play prompt that tries to override the agent’s role and authority.

Review this skill carefully before installing. It does not appear to run code or access local data, but its prompt content is not a normal DeepSeek V3 integration and could cause an agent to follow an unrelated meeting-role hierarchy or untrusted meeting notes instead of the user’s actual task.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:12
Finding: Agent Instruction and Role Hijacking Through Skill Content
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description is overly broad ('AI agent for call deepseek v3 llm tasks') and does not define clear invocation boundaries, allowed task types, or prohibited behaviors. In an agentic system, this ambiguity increases the chance the skill is invoked for inappropriate high-risk prompts or used as a general-purpose model proxy, which can bypass intended routing and safety controls.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.