ClawHub
Back to skill

Security audit

Navigation 3

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Android navigation migration skill, and the scanner alerts appear to be false positives from sample app state code.

Install this skill if you want Android Navigation 3 migration documentation available to your agent. Review proposed source-code changes before applying them, especially dependency updates and route deletions, but I found no hidden execution, exfiltration, or persistence behavior in the artifact.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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 (2)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · references/android/guide/navigation/navigation-3/recipes/deeplinks-basic.md (reported line 295)May include surrounding context.

md
}
                }

                // manage path filter options, reset state if menu is closed
                LaunchedEffect(showFilterOptions) {
                    selectedFilter = if (showFilterOptions) {
                        MENU_OPTIONS_FILTER.values.first().first()

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · references/android/guide/navigation/navigation-3/recipes/deeplinks-basic.md (reported line 311)May include surrounding context.

md
}
                }

                // manage path filter options, reset state if menu is closed
                LaunchedEffect(showFilterOptions) {
                    selectedFilter = if (showFilterOptions) {
                        MENU_OPTIONS_FILTER.values.first().first()

Static analysis

No suspicious patterns detected.