Security audit
results-structure-diagnoser
Security checks across malware telemetry and agentic risk
Overview
This skill is a structured writing-assessment helper for psychology Results sections and does not request unusual access or background behavior.
Before installing, consider that the skill is intended for manuscript text analysis, so users should only provide Results sections they are allowed to share with their agent environment. The artifact itself is coherent and does not request credentials, broad file access, or automatic actions.
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
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.