Back to skill

Security audit

Alphagbm Compare

Security checks for vulnerabilities and agentic risk

Overview

This is a finance comparison guidance skill with no executable code, persistence, credential access, or hidden behavior, though its trigger phrases are broader than ideal.

Installers should understand this skill may activate on broad comparison phrasing and can produce stock or options recommendations; use it for explicit finance comparisons and verify financial conclusions independently before acting.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger set includes very generic phrases such as 'versus', 'which is better', 'side by side', and 'best value stock', which are likely to match ordinary conversation outside the intended finance-comparison use case. Overbroad activation can cause the wrong skill to intercept user requests, producing unintended financial recommendations or displacing a more appropriate skill.

Content

No source excerpt is available for this finding.