Security audit

Report Summary Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed report summarizer that reads daily Markdown reports and writes weekly or monthly summaries, with no evidence of hidden code, exfiltration, privilege escalation, or destructive behavior.

Install this if you want a Chinese-language report summarizer for daily Markdown files under /data/reports. Before scheduled use, confirm the /data/reports paths match your environment and that overwriting weekly or monthly report files is acceptable.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The README presents the skill name, usage instructions, trigger phrases, and operational notes entirely in Chinese. This effectively forces a specific language/locale for users without opt-in or justification, which matches the language/locale policy violation criteria.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger phrases are broad and can cause the skill to activate on loosely related user requests without clear exclusion conditions or confirmation. In a file-writing skill, unintended invocation matters because it can read from a report directory and generate/save output automatically, creating unexpected side effects or overwriting user-expected workflow.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill directs the agent to save generated content to fixed filesystem paths without warning the user or requiring confirmation. Automatic writes to predetermined locations can surprise users, overwrite existing reports, or be abused through accidental invocation, making the behavior more risky in this context because the skill is explicitly user-invocable and persistent-output oriented.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The instructions require a particular Chinese reporting style and prescribed wording, such as preferred verbs and banned colloquial expressions, without indicating that the user can choose another language or register. This is a natural-language policy concern because it forces a specific language/locale style rather than making it optional or context-justified.

Intent-Code Divergence

Low

Confidence: 93% confidence
Finding: 清单前文与 manifest 一致地限定该技能用途为读取已有日报并生成周报或月报，但 L104 明确写到“在生成日报时”，把技能描述成日报生成器。这不是单纯遗漏，而是对技能意图的直接混淆，可能导致执行时偏离既定用途。

Natural-Language Policy Violations

Low

Confidence: 96% confidence
Finding: The manifest description is written as a Chinese-only instruction: '基于已有日报自动汇总生成周报和月报'. This indicates a language-specific skill presentation without any indication that users can choose another language or that the locale restriction is intentionally documented for a specific regional use case.

Static analysis

No suspicious patterns detected.