Back to skill

Security audit

Model Rate Limiter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed model/API request rate-limit helper that uses a workspace state file and shows no evidence of hidden code, exfiltration, or destructive behavior.

Install this if you want workspace-level model request throttling. Before enabling it, confirm the limit you want and remember that changes to rate-limit-state.json may affect later model requests until disabled or reset.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list includes broad natural-language terms such as "限速" without clearly constraining that the skill applies specifically to model/API request limiting. This can cause accidental activation in unrelated contexts, leading the agent to modify persistent rate-limit state unexpectedly and affecting future request handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The natural-language description, instructions, and example dialogues are entirely in Chinese, and the trigger phrases are also Chinese-only. There is no indication that the skill is region-specific or that users may choose another language, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill directs modification of a persistent workspace file that changes future behavior, but it does not disclose persistence or require confirmation. Users may unknowingly enable, disable, or reset throttling in a way that outlives the current interaction, which can weaken operational controls or cause confusing behavior later.

Content

No source excerpt is available for this finding.