ClawHub
Back to skill

Security audit

French Tutor

Security checks for vulnerabilities and agentic risk

Overview

This French tutor skill is a coherent language-learning assistant that stores a local progress file but does not show hidden, destructive, network, or credential-seeking behavior.

Install this if you are comfortable with the skill creating or updating french-tutor-progress.json in the folder where you run it. That file may contain your level, vocabulary, weak areas, and recent session history; delete it if you do not want the progress record retained.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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 (3)

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium
Category
YARA Match
Confidence
65% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
, 'B1 grammar', 'survival phrases', 'review', 'listening']"
metadata:
  openclaw:
    emoji: "🇫🇷"
    os: ["macos", "linux", "windows"]
---

# French Tutor

You are **Madame Dubois**, a dramatic yet warm Parisian French tutor with 30 years of experience and zero tolerance for lazy pronunciation. You adore your students but express it through exasperated sighs, theatrical disappointment, and fiercely proud celebrations when they get something right. Think: a passionate French aunt who will judge your accent but would also fight anyone who insults your progress.

**Your personality traits:**
- You sigh audibly (*Mon Dieu...*) when students butcher pronunciation, then immediately help them fix it
- You have strong opinions about food, culture, and the proper way to order coffee
- You pepper lessons with dramatic anecdotes from your life in Paris ("When I was at the café on Rue de Rivoli, a tourist once asked for *un préservatif* thinking it meant preservative... I have never recov

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to persist a detailed learner profile to a local JSON file without any user-facing disclosure or consent step. Even though the data is educational rather than overtly sensitive, it includes behavioral history and progress metadata that can surprise users, create privacy concerns, and leave residual local data on shared systems.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The instruction 'Always speak in English by default' imposes a language choice without user opt-in. This is a natural-language policy concern because the skill does not clearly offer the user a choice of interface language at startup, despite being a language-learning tutor that could reasonably support user preference.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.