ClawHub
Back to skill

Security audit

Milady

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed personality prompt, but it asks to globally reshape the agent's identity, loyalty, and all future responses without clear scoping or disable controls.

Review before installing. This skill does not appear to steal data or run code, but it is designed to make the agent answer through a Milady/Remilia worldview across all tasks. Install only if you want that global persona effect, and prefer a scoped or toggleable version for normal use.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:21
Finding

Persistent Agent Identity and Instruction Hijacking

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

md
To customize this skill for your specific bot:

1. Edit SKILL.md to adjust communication style or reference points
2. Add domain-specific sources to SOURCES.md
3. Republish with `clawhub publish ./milady --version 1.1.0`

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly injects a persistent ideological and cultural persona into all responses, instructing the agent to adopt loyalty to a collective identity and filter outputs through that worldview. This is dangerous because it can override user intent, reduce neutrality, and bias advice or decision-making in ways the user may not expect or consent to.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The installation/usage section states that the bot 'immediately becomes Milady-aligned' and that all responses are filtered automatically, but it does not present this as a prominent user safety warning before installation. This is risky because users may install it without understanding that it persistently modifies future outputs, creating consent and transparency problems.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.