Security audit
SCI/SSCI Polishing
Security checks for vulnerabilities and agentic risk
Overview
This skill is a focused academic translation and polishing helper with a small local audit script and no evident hidden data access or unsafe behavior.
Before installing, expect this skill to guide an agent through manuscript polishing and to optionally run a local Python audit on text you provide. It does not appear to request credentials, network access, or broad filesystem access, but users should still avoid supplying confidential manuscript text unless their agent environment is appropriate for that data.
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
Static analysis
No suspicious patterns detected.