Security audit
Kano Model
Security checks for vulnerabilities and agentic risk
Overview
This skill is a Kano requirements-analysis guide with no evident malicious behavior, but its referenced helper script and reference files are not included in the inspected package.
Before installing, note that the skill appears security-benign but incomplete: it tells the agent to use scripts/kano_analyzer.py and several references/ files that are not present in this package. Expect the skill to need those missing files or to fall back to manual Kano calculations; review any separately supplied script before running it.
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
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep