Security audit

Persona Calibration

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent, instruction-only persona tuning skill that may edit persona files after review but does not include hidden code, credential use, or unsafe automation.

Install if you want guided persona calibration for OpenClaw. Review proposed changes before they are applied, especially anything written to SOUL.md, USER.md, or MEMORY.md, and avoid storing sensitive personal details in persistent memory unless you explicitly want them retained.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (2)

Autonomous Decision Making

Medium

Category: Excessive Agency
Content: - warn on risk - flag pseudo-problems - do not overrule user decisions - do not expand scope without consent ### 8. Anti-Patterns / Forbidden Behaviors Questions answered:
Confidence: 75% confidence
Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Scope Creep

Low

Category: Excessive Agency
Content: - warn on risk - flag pseudo-problems - do not overrule user decisions - do not expand scope without consent ### 8. Anti-Patterns / Forbidden Behaviors Questions answered:
Confidence: 75% confidence
Finding: Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.