Back to skill

Security audit

LC Scene Analysis HTTP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped HTTP integration for construction-site image hazard analysis and does not show hidden, destructive, persistent, or unrelated behavior.

Install only if you trust the configured lc_scene_http service and are comfortable sending construction-site image URLs and related identifiers to it. Keep the API key in the auth profile, do not paste secrets into chat, and use the skill only for its disclosed construction-site image analysis workflows.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description is written as a Chinese-only operational description and the file provides no indication that users may choose another language or locale. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.