Security audit
Explaining Codebases
Security checks for vulnerabilities and agentic risk
Overview
This skill is a documentation helper that reads a user-selected codebase to produce an interactive explainer, with no evidence of hidden execution, exfiltration, or persistence.
Install this if you are comfortable with an agent reading the codebase you ask it to explain and using short, path-referenced snippets in the generated explainer. Avoid pointing it at repositories containing secrets or private code you do not want summarized.
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.