ClawHub
Back to skill

Security audit

Reddi Agent Evaluation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a lightweight agent-evaluation guidance skill with no executable payload or hidden behavior found.

Install this if you want guidance for designing agent evaluations and reliability tests. Be aware it may activate for broad agent-testing requests, and any actual LLM API scoring would depend on your configured environment rather than code shipped in this skill.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 'Use when' list includes generic phrases like 'agent testing', 'agent evaluation', and 'test agent' without defining boundaries, exclusions, or a narrow activation context. These terms are broad enough to match many ordinary requests and could cause unintended skill invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.