Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- SKILL.md:54
Security audit
Openclaw Context Capsule
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed local context-compression plugin, with no artifact evidence of hidden network access, filesystem access, credential theft, or destructive behavior.
Before installing, understand that this plugin reads and transforms your OpenClaw conversation history and may place summarized older history into the model's system context. Its redaction is best-effort, and older wording can be lost, so avoid using it as the only protection for highly sensitive or exact-transcript workflows.
SkillSpector
By NVIDIA
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
VirusTotal
65/65 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.prompt_injection_instructions