Back to skill

Security audit

ilc

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ILC setup and routing guide with no bundled executable code or hidden agent behavior.

Before installing, verify the PyPI package or GitHub source yourself, and only run enrollment or submission commands when you intend to create a local ILC identity or write to a local graph workspace.

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

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

In the markdown section describing "What You Can Do," the file lists many broad actions the skill can perform but does not specify clear trigger phrases, scope boundaries, or examples of when the skill should not activate. For a markdown skill description, this can create ambiguity about when requests related to installation, contact, enrollment, or graph submission should invoke this skill versus ordinary conversation about the project.

Content

No source excerpt is available for this finding.