Security audit

Course

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for course management, but it encourages student tracking, automated outreach, and community moderation without clear privacy, consent, or user-control boundaries.

Review this skill before installing if you will use it with real students. Require explicit student-facing privacy notices, minimize collected data, set retention and access controls, confirm any automated email/community actions before they run, and keep human review for moderation or account-affecting decisions.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (5)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly supports enrollment tracking, progress monitoring, automated reminders, and certificate generation, all of which imply handling student personal and behavioral data. Without a privacy, retention, access-control, or consent warning, the skill could encourage collection or processing of sensitive student information in ways that violate user expectations, policy, or applicable privacy regulations.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill specifies collection and ongoing tracking of student activity, assessment data, support interactions, and community participation without any notice, consent flow, or data-handling boundaries. In an education context this creates privacy and compliance risk because users may be monitored and profiled beyond their expectations, especially when participation and inactivity are tracked over time.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: Automated flagging of negative sentiment means user-generated community content is being analyzed for moderation purposes, yet the document gives no warning that posts may be algorithmically monitored. In a student community this can chill speech, produce false positives, and expose sensitive personal or emotional disclosures to additional review without participants understanding that automated analysis is occurring.

Missing User Warnings

Low

Confidence: 91% confidence
Finding: The skill directs creation of a workspace under ~/courses/ but does not clearly warn that using the skill may create or modify files on the user's local filesystem. While this is expected behavior for a course-management skill, the lack of explicit notice can lead to unintended writes, overwriting existing material, or user surprise in environments where filesystem changes require consent.

Missing User Warnings

Low

Confidence: 83% confidence
Finding: The automated nudge sequence defines proactive outreach based on inactivity without clearly informing students that their engagement will be monitored and used to trigger contact. While common in course platforms, undisclosed behavioral-triggered messaging can undermine user trust and may create consent or anti-spam concerns depending on jurisdiction and channel used.