ClawHub
Back to skill

Security audit

Firm Skill Loader Pack

Security checks for vulnerabilities and agentic risk

Overview

This skill only documents local skill search and lazy-loading behavior, with no bundled executable code or hidden instructions found.

Install this only if you are comfortable with a loader/search skill reading SKILL.md files from your local skills directory. Also review and trust the required mcp-openclaw-extensions dependency, since the inspected artifact itself only contains documentation for using those tools.

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
  • 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
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The warning text is written only in French, which imposes a specific language in the skill's natural-language documentation without any opt-in or alternative. The file does not indicate that the skill is region-specific or that users may choose another language, which conflicts with the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.