Security audit
verify-before-answer
Security checks for vulnerabilities and agentic risk
Overview
This skill transparently tells the agent to verify factual claims with searches, documents, or runtime evidence before answering.
Before installing, understand that this skill may make your agent search the web or check local project/runtime evidence before answering factual questions. That behavior is disclosed and aligned with the skill's purpose; review command outputs before sharing them if your workspace contains sensitive details.
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.