Security audit

Context Slimming

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill is coherent, but it asks agents to rewrite and commit persistent workspace context files that can shape future agent behavior.

Install only if you want an agent to help edit persistent OpenClaw workspace context. Ask for a plan first, keep backups, review diffs before applying changes, avoid storing actual secrets in injected markdown, and manually approve deletions, moves, and commits.

SkillSpector

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

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: references/checklist.md:35