T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:35- Finding
Overly Broad Confirmation-Free Execution Policy
- Content
View full analysis
- Remediation
View remediation
Security audit
Accessibility Toolkit 1.0.0
Security checks for vulnerabilities and agentic risk
Overview
The skill is documentation-only and accessibility-focused, but it recommends risky smart-home patterns such as automatic front-door unlocking and broad confirmation-free actions.
Review and harden this skill before installing it into any agent with smart-home authority. Do not copy the automatic unlock template as written; require explicit authenticated approval or multiple local presence signals for locks, avoid exposing access codes in chat or notifications, and limit confirmation-free behavior to a clear allowlist of low-risk actions.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (3)
T09 · Insecure Skill Coding Practices
Error
- Location
SKILL.md:76- Finding
Exterior Door Automatically Unlocked from a Single Location Event
- Content
View full analysis
- Remediation
View remediation
T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:136- Finding
Plaintext Access Code Included in an Error-Reporting Template
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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
Findings (5)
Missing User Warnings
High
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill includes an arrival automation that automatically unlocks the front door based on zone entry, but it provides no warning about spoofing, geofencing errors, shared-device compromise, or unsafe timing. In a smart-home accessibility context, this can create a physical security risk by exposing the residence to unauthorized entry if the trigger is misfired or abused.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The guidance says to avoid confirmation for broad voice-triggered actions and to 'just do it,' without warning about accidental activation, misrecognition, spoofed voice input, or commands issued in unsafe contexts. In an accessibility-focused, voice-first system, those risks are amplified because high-trust automation may control locks, notifications, media, and environment settings.
- Content
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 89% confidence
- Finding
The skill explicitly promotes autonomous execution without confirmation, which is a real decision-making and control-risk pattern in an environment that may trigger home automations and communication changes. Although intended to reduce friction for disabled users, removing confirmation wholesale can cause harmful unintended actions when speech recognition is wrong or commands are ambiguous.
- Content
"Goodnight" → Bedtime scene, lock doors, set thermostat, silence notifications "I'm working" → Focus mode, desk lights, DND, close distracting tabs "Movie time" → Dim lights, TV on, adjust audio "Help" → Immediate attention, no confirmation dialogs
text **Never require confirmation for reversible actions.** Just do it. They can say "undo" if wrong.
Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Confidence
- 75% confidence
- Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- Content
✓ Doors locked ✓ Thermostat 68°F
No confirmation needed — all reversible with one word.
text ## Scripts
Ssd 3
Medium
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The script description states that conversation history is analyzed to identify repeated requests, implying retention or review of prior user interactions without any stated limits, consent, minimization, or retention policy. For a disability-support skill, conversations may contain highly sensitive health, schedule, and household information, increasing privacy and compliance risk.
- Content