ClawHub
Back to skill

Security audit

Office Document Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill reads user-supplied office documents and uses disclosed local extraction tools without hidden network, persistence, or destructive behavior.

Install this if you want local text extraction for office files. It will read the document paths you provide and may invoke local OCR or conversion tools, so use it only on files you are comfortable giving to the agent and expect imperfect results for scanned PDFs, legacy Office files, charts, and complex layouts.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the agent to invoke shell commands and local Python scripts, but it does not declare any explicit tool scope such as allowed-tools or permissions. That creates an overbroad execution surface: if this skill is selected in an environment with shell access, it can run commands against attacker-supplied document paths and external utilities without a clear policy boundary, increasing the risk of unintended command execution or unsafe file handling.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
return RECOMMENDED_LANGS[:]

    try:
        r = subprocess.run(
            ["tesseract", "--list-langs"],
            stdout=subprocess.PIPE,
            stderr=subprocess.PIPE,
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
def run(cmd):
    return subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)


def available_tess_langs():
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The code defines `RECOMMENDED_LANGS = ["chi_sim", "eng"]`, which embeds a specific language/locale preference in natural language-facing behavior. Under the policy, forcing a specific language or locale without opt-in can be a violation unless clearly justified as region-specific.

Static analysis

No suspicious patterns detected.