Security audit
Building Onboarding Workflows
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent Sendly workflow helper that uses expected Sendly tools and requires explicit user approval before live or destructive workflow changes.
Before installing, users should understand that this skill can create and modify Sendly workflow automations and may affect real customer emails once enabled. Its instructions include appropriate approval gates, so use it with a connected Sendly account whose OAuth scopes match the workflows you intend to manage.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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.