Security audit
risk-aware-retry
Security checks for vulnerabilities and agentic risk
Overview
This skill provides coherent retry guidance for flaky operations and explicitly tells the agent to stop for destructive or security-sensitive actions.
Before installing, understand that this skill encourages automatic retries for low-risk reversible failures, but it also instructs the agent to notify on medium-risk actions and ask before destructive, security-sensitive, or irreversible actions.
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.