Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:86
Security audit
Sandbox & Blast-Radius Control Engine X∞
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed safety-policy skill that guides agents to limit risk, verify actions, protect secrets, and recover safely; it does not include executable code or hidden install behavior.
Before installing, understand that this skill may make the agent pause for previews, confirmations, backups, and verification on risky tasks. That is consistent with its security role. Review any configured observability or evaluation integrations in your OpenClaw environment so audit/checkpoint data stays local or goes only where you expect, and avoid storing secrets in traces or logs.
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
Detected: suspicious.prompt_injection_instructions