Back to skill

Security audit

Elevator Outage Access Plan

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only elevator outage planning skill with clear safety boundaries and no executable, network, credential, or persistence behavior.

Before installing, treat this as a logistics template only. Avoid entering unnecessary medical or resident-identifying details, follow official building instructions, and use emergency services or building emergency contacts for trapped people, injury, distress, fire, smoke, power hazards, or unsafe stair use.

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
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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The acceptance criteria explicitly require public-facing documentation to be English only. This is a natural-language policy constraint that forces a specific language choice, and the file does not indicate user opt-in or a documented compliance-based reason for the restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The language audit states that content must be English only, reinforcing a mandatory locale policy. Under the policy rules, forcing a specific language without offering choice or clear justification is a reportable issue.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The trigger phrase "building access coordination" is much broader than the skill's stated purpose of planning for elevator outages. Because it lacks the outage-specific constraint present in the other triggers, it may cause unintended invocation for generic access, security, or facilities requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest sets "language": "en", which implies the skill is fixed to English. Under the policy, language constraints should offer user choice or be clearly documented as necessary for a region-specific or compliance-specific use case, which is not stated here.

Content

No source excerpt is available for this finding.