ClawHub
Back to skill

Security audit

Accounting Workflows

Security checks for vulnerabilities and agentic risk

Overview

This is a local accounting workflow skill with disclosed financial-document handling and no evidence of hidden email access, network access, or persistence.

Install this only if you are comfortable storing and processing accounting documents in the configured local data directory. Review the OPENCLAW_DATA_DIR location, approve any sudo package install yourself, and use separate companion skills for email, OCR, government filings, or accounting-software exports only with scoped credentials and clear retention rules.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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
Findings (4)

Missing User Warnings

High
Confidence
95% confidence
Finding
The automated email-monitoring scenario involves processing potentially sensitive emails and attachments, yet the prompt provides no warning or safeguard around privacy, confidentiality, consent, or handling of financial records. In this context, users may enable broad document ingestion without understanding that personal, financial, or unrelated mailbox content could be accessed, classified, stored, and surfaced in summaries or alerts.

Chaining Abuse

High
Category
Tool Misuse
Content
export OPENCLAW_DATA_DIR="/data"

# 2. Ensure jq is installed (used for JSON processing)
which jq || sudo apt install jq

# 3. Create the directory structure
mkdir -p $OPENCLAW_DATA_DIR/{incoming/{invoices,receipts,statements,government},processing,clients}
Confidence
75% confidence
Finding
Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The prompt requests a 'daily email monitoring system' that automatically scans emails and attachments for financial documents, but it does not define scope boundaries such as which mailbox, senders, folders, retention limits, or approval steps apply. That ambiguity can enable over-collection and over-processing of sensitive messages and attachments beyond the user's intended accounting workflow, creating privacy and data-minimization risk.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Content
export OPENCLAW_DATA_DIR="/data"

# 2. Ensure jq is installed (used for JSON processing)
which jq || sudo apt install jq

# 3. Create the directory structure
mkdir -p $OPENCLAW_DATA_DIR/{incoming/{invoices,receipts,statements,government},processing,clients}
Confidence
70% confidence
Finding
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.