ClawHub
Back to skill

Security audit

Agente Biologia

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward biology tutoring skill with a somewhat broad activation rule but no hidden code, privileged actions, persistence, or data access.

Installing this skill should be low risk. Be aware that it may activate whenever biology-related topics come up, so users who only want it for explicit FUVEST biology study sessions may prefer narrower trigger wording.

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
96% confidence
Finding

The trigger condition is broad enough to activate on essentially any ordinary mention of biology-related topics, which can cause the skill to be invoked outside narrowly intended contexts. In an orchestrated agent environment, over-invocation can hijack routing, crowd out more appropriate skills, and increase the chance that this agent influences responses when the user did not explicitly request it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.