Security audit
Content Research & Sourcing
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed research-checking workflow that helps verify claims and citations before content is published.
Install only if you want agents to check factual claims, citations, and attribution before publishing. Review the maintained source log yourself, especially for health, finance, legal, or public-facing claims, and re-check time-sensitive statistics before scheduling content.
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.