Security audit

Personal Goals

Security checks for vulnerabilities and agentic risk

Overview

This goal-tracking skill is coherent and not malicious, but it can read and update persistent personal-goal memory on very broad triggers without an explicit confirmation step.

Install only if you are comfortable with the agent maintaining a persistent goals file that may include sensitive life, health, finance, career, or relationship information. Before using it broadly, narrow the trigger conditions and require confirmation before writing updates to knowledge/personal/goals.md.

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

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The README presents the skill's purpose, capabilities, and commands exclusively in Russian. This can violate a language/locale policy when the skill forces a specific language without user opt-in and does not state that it is intentionally region- or language-specific.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger description is very broad, including common words like "goal," "plan," "progress," and "I want to," which can cause the skill to activate in many unrelated personal conversations. Over-broad invocation increases the chance the skill will read or update personal goal memory when the user did not intend to use this capability, creating privacy and integrity risks through unintended context capture.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The operational instructions and user-facing content are written in Russian, indicating the skill is designed to respond in a specific language. There is no statement that the user may choose another language or opt into Russian, which can violate language/locale policy requirements.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill instructs itself to update `knowledge/personal/goals.md` whenever the user sets a new goal or reports progress, but it does not require notifying the user or obtaining confirmation before writing persistent memory. This can lead to silent storage or modification of sensitive personal information such as health, finances, relationships, or career plans, which is a meaningful privacy and data-integrity concern.

Static analysis

No suspicious patterns detected.