Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- docs/configuration.md:71
- Evidence
the system prompt:
Security audit
Lossless Context Management
Security checks for vulnerabilities and agentic risk
Overview
This plugin persistently stores and summarizes OpenClaw conversation history for recall, and the sensitive behavior is disclosed and aligned with that purpose.
Install only if you want OpenClaw conversations, tool outputs, and large pasted content retained in a local LCM database for later recall. Review session exclusion/stateless patterns, database and large-file paths, LLM model policy, and cleanup/repair commands before using it on highly sensitive chats.
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