ClawHub
Back to skill

Security audit

Persona Calibration

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed persona-calibration workflow that may update OpenClaw persona and memory files with user approval.

Install this if you want a structured interview-driven process for tuning OpenClaw persona files. Review proposed edits before applying them, especially changes to MEMORY.md or rules that will affect future agent behavior.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The phrase "I want a better personality" is intentionally described as vague, but the skill does not provide negative examples or clearer limits on when this should versus should not invoke the workflow. Because this wording overlaps with broad conversational requests, it risks unintended activation for general self-improvement or stylistic feedback requests.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
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.

Content

Scanner excerpt · references/persona-dimensions.md (reported line 115)May include surrounding context.

md
- warn on risk
- flag pseudo-problems
- do not overrule user decisions
- do not expand scope without consent

### 8. Anti-Patterns / Forbidden Behaviors
Questions answered:

Scope Creep

Low
Category
Excessive Agency
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.

Content

Scanner excerpt · references/persona-dimensions.md (reported line 115)May include surrounding context.

md
- warn on risk
- flag pseudo-problems
- do not overrule user decisions
- do not expand scope without consent

### 8. Anti-Patterns / Forbidden Behaviors
Questions answered:

Static analysis

No suspicious patterns detected.