Security audit

05 Monthly Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a report-writing template for internal compliance monthly reports and does not install code, run commands, persist data, or send data elsewhere.

Install only if you intend to use it for internal compliance report drafting. Provide aggregated or redacted data where possible, and do not paste personal data, customer identifiers, confidential legal material, or sensitive incident details unless your organization has approved that use.

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 (2)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger condition is very broad ('每月末或管理层需要时，用户提供月度数据，生成完整月报'), which creates unclear invocation boundaries and increases the chance the skill is used in unintended contexts or with incomplete/overbroad datasets. While not directly exploitable like code execution, ambiguous activation can cause accidental processing of sensitive internal data and reduce operator control over when the skill should be used.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly solicits sensitive operational, complaint, supplier-risk, incident, media, legal, and regulatory information, but it provides no confidentiality notice, data-handling constraints, minimization guidance, or restrictions on pasting personal or case-level details. In an internal compliance context, this makes accidental disclosure, oversharing, or inappropriate processing of sensitive business and potentially personal data substantially more likely.

Static analysis

No suspicious patterns detected.