Security audit

Action Items

Security checks for vulnerabilities and agentic risk

Overview

This meeting-notes skill is coherent and purpose-aligned, with the main caution that saved follow-up history may include sensitive meeting details.

Install this if you want Portuguese meeting notes turned into task lists. Before saving follow-up history, confirm what will be stored, avoid highly sensitive meeting content unless appropriate for your workspace, and ask the agent not to persist your identity or action history if you only need a one-time extraction.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger section includes broad, everyday phrases such as asking what is pending from a meeting, which can cause the skill to activate in situations where the user did not explicitly intend to invoke it. Because the skill can then read/write meeting-derived task data and potentially prompt for saving follow-up history, unintended invocation increases the risk of overcollection, accidental persistence, and user confusion.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill proposes maintaining follow-up history in memory for later meetings, but it does not clearly warn users that meeting content may be retained across sessions. Meeting notes often contain sensitive business, personnel, or project information, so silent retention creates a privacy risk and may violate user expectations or internal data-handling policies.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The description, triggers, extraction rules, and examples are all Portuguese-specific and rely on Portuguese phrases such as "precisamos", "fica pra", and "semana que vem". There is no indication that users can choose another language or that the skill is intentionally limited to Portuguese for a documented reason.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill instructs asking 'Who are you in the meeting?' and saving that identity in memory, but it does not provide a privacy notice or obtain explicit consent for storing personal identity information. Even if limited in scope, this is personal data collection tied to workplace context and can be sensitive when retained for future use.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.