Security audit
Research Claim Ledger
Security checks for vulnerabilities and agentic risk
Overview
This is a text-only research auditing skill that helps check claims against sources and shows no hidden code or system-level behavior.
This skill is appropriate to install if you want an agent to audit research claims and citations. Because it is designed to review drafts and source packets, only provide documents you are comfortable having the agent analyze, and keep any web searching or source discovery under your direction.
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.