Back to skill

Security audit

weekly-report-auto

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed weekly-report helper that reads local Markdown daily reports from a specific folder and summarizes them, with no evidence of hidden execution, exfiltration, or persistence.

Before installing, confirm that the configured WorkBuddyFile folder contains only Markdown daily reports you are comfortable having the agent read and summarize. Be aware that asking for a weekly summary can cause the skill to scan that folder automatically.

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
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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description does not clearly warn users that it will automatically scan and read all matching local Markdown files from a fixed personal directory. This weakens informed consent and increases the chance that users unknowingly expose personal or sensitive work content, especially because the scan is automatic and recursive.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are very broad and map to ordinary requests like generating or organizing a weekly summary, which can cause the skill to activate when the user did not specifically intend local file scanning. In this skill, unintended activation is more dangerous because activation leads to automatic recursive reading of Markdown files from a fixed personal directory, creating a privacy and consent risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill name is specified only in Chinese ("周报"), which suggests a fixed language presentation. In this metadata file there is no indication of user language choice, opt-in, or documentation that the skill is intentionally region-specific.

Content

No source excerpt is available for this finding.