Security audit
branddock-on-brand
Security checks for vulnerabilities and agentic risk
Overview
This skill gives clear, purpose-matched instructions for using Branddock to retrieve brand context, draft content, score it, and leave approval to the human.
Install this if you use Branddock and are comfortable letting the agent access Branddock brand data and submit drafts for scoring or generation. Review credit-consuming actions before approving them, and avoid placing API keys directly in chats unless your client handles secrets safely.
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.