Security audit
Candidate Scorecard
Security checks for vulnerabilities and agentic risk
Overview
This is a straightforward interview-scorecard writing skill with no hidden execution, persistence, or data-transfer behavior in the artifact.
This skill appears safe to install for drafting structured interview feedback. Because it may process sensitive candidate information, users should provide only relevant job-related evidence and review outputs for fairness, accuracy, and compliance with their hiring policies.
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.