Security audit

AI Address Parser

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for adding an LLM-based address parser, with disclosed external API use and non-destructive form updates.

Before installing, confirm your app is allowed to send pasted address, contact, and phone data to the configured LLM provider, keep the API key server-side, and adjust the country/language normalization rule if your product uses a different locale or country format.

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

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: 89% confidence
Finding: Line L043 instructs the skill to normalize country values to the full English country name. This imposes a specific language choice in natural-language behavior without any user opt-in or clear region-specific justification, which matches the language/locale policy violation criteria.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.