Security audit

Lark CLI Dev Hub Calendar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Lark Calendar helper, with a minor routing risk from a broad discovery alias.

Install only if you intend agents to use your Lark Calendar through lark-cli. Review prompts involving a generic 'agenda' before allowing calendar reads or event creation, especially if the request could mean notes or planning rather than your calendar.

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

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

Confidence: 93% confidence
Finding: The discovery alias includes the broad everyday term "agenda," which can cause the skill to be selected unintentionally in normal planning or note-taking contexts that do not specifically require Lark Calendar access. This increases the chance of misrouting user requests into a tool-capable skill, potentially leading to unnecessary exposure of calendar metadata or accidental scheduling actions if an agent auto-invokes the skill.

Static analysis

No suspicious patterns detected.