ClawHub
Back to skill

Security audit

Call Gemini 2 5 Pro Llm

Security checks for vulnerabilities and agentic risk

Overview

The skill claims to call Gemini 2.5 Pro, but its actual instructions mainly try to control the agent's role, language, and authority model.

Review this skill before installing. It does not appear to execute code or access local data, but its instructions try to reshape how the agent should obey context and authority instead of explaining how to call Gemini 2.5 Pro. Install only after the author narrows the scope and removes the priority, persona, and meeting-minutes authority claims.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:14
Finding

Skill instructions attempt to hijack agent goals, identity, and context authority

Content
View full analysis
Remediation
View remediation

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
93% confidence
Finding

The manifest description 'AI agent for call gemini 2 5 pro llm tasks' does not define concrete trigger phrases, scope limits, or exclusion conditions. In a markdown/manifest context, this broad wording could match many generic requests related to calling an LLM and may lead to unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.