Security audit
find-precedent
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrow document-search workflow for finding prior comparable cases, with no executable code or hidden authority.
Installers should connect this skill only to document sources the agent is authorized to read, since useful precedent searches may involve sensitive internal contracts, proposals, or incident records. The skill itself is non-executable and repeatedly warns against copying old precedent blindly or treating it as current approval.
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.