ClawHub
Back to skill

Security audit

go-latitude-llm

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documented helper for using an unofficial Go client for the Latitude LLM API, with sensitive API capabilities disclosed and bounded by user-directed use.

Install only if you intend to use this unofficial Go client with a Latitude organization. Treat API keys, OAuth tokens, trace contents, exports, and member/API-key management operations as sensitive, and use write, revoke, delete, invite, or export calls only when you explicitly intend those organization changes.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

Because no manifest is available, the skill's purpose is unknown, so this file is evaluated against documented capabilities alone. The operations list advertises extensive account, member, API key, OAuth key, project, issue, and export functionality, which are powerful capabilities not justified by any stated skill purpose in the provided context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.