Security audit

REGULATORYCHANGEMONITOR

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently monitors public regulator websites and keeps a small disclosed local state file to avoid duplicate alerts.

Before installing, be aware that the skill is intended to run daily, access public regulator websites, and maintain a small last-run.md state file. Review or adjust the listed regulators, focus sectors, and alert threshold to match your compliance needs.

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)

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill explicitly instructs the agent to create or update last-run.md in the workspace but does not warn the user that running the skill will modify local state. This is not overtly malicious, but silent workspace writes can surprise users, create auditability issues, and normalize file modification without consent, especially for scheduled runs.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.