Back to skill

Security audit

roundtable-forum

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language roundtable discussion helper, with no artifact-backed evidence of malicious code, data theft, or destructive behavior.

Install this only if a Chinese-language discussion workflow fits your needs. Before relying on the documented Cron reminder or saved output behavior, verify whether the installed package adds any scheduler entry, and avoid putting sensitive topics into generated knowledge-network files if you later enable file saving.

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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README states that a Cron-based automatic reminder is configured to run daily at 20:00, but it does not explain what process is scheduled, whether it persists after installation, or what system/user impact it may have. Undisclosed scheduled execution can surprise users, create unwanted persistence, and may run in contexts with access to local data or user sessions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file presents all headings, instructions, commands, and examples exclusively in Chinese, which effectively forces a specific language/locale for use. The policy allows locale constraints only when users are given a choice or when the restriction is clearly documented and justified, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill hard-codes all prompts, commands, and interaction flow in Chinese without offering a language selection or documenting a locale-only requirement. This can exclude users, cause misunderstanding of commands, and create unsafe operation or consent issues if users cannot accurately interpret instructions or outputs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The README says knowledge-network files are saved under the output directory but does not warn that these files may contain user-supplied topics or derived sensitive content from discussions. Silent local persistence can expose private prompts or research subjects to other local users, backups, or version control if the directory is later shared.

Content

No source excerpt is available for this finding.