Back to skill

Security audit

表格创作编排美化

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because a helper script may run attacker-controlled Python if its path can be influenced; the scan was partial, so the evidence is incomplete.

Consider the conditional helper-script execution risk and the undeclared tool scope before installing. The scan inspected all listed components but was marked partial because several referenced paths were missing, so the evidence is incomplete.

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
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (4)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, file_write, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
86% confidence
Finding

The subprocess uses an argument list, so workbook filenames do not create shell injection; however, its Python script is selected from EXCEL_RECALC_SCRIPT or ancestor-directory discovery with only an is_file check. If an attacker can influence that environment variable or plant a matching script in a searched directory, a recalculation request executes attacker-controlled Python with the agent's privileges. Formula recalculation is a normal part of this skill's workflow, making this conditional script-hijacking path relevant.

Content

Scanner excerpt · scripts/beautify.py (reported line 193)May include surrounding context.

python
"message": "未找到内置 recalc.py;已设置 fullCalcOnLoad,Excel/WPS 打开时会自动重算,但第三方预览器仍可能显示空白",
        }
    try:
        proc = subprocess.run(
            [sys.executable, str(script), str(xlsx), "60"],
            capture_output=True,
            text=True,

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · scripts/theme_engine.py (reported line 859)May include surrounding context.

python
color=chart_rgb(theme.accent_light),
                showValue=True,
                minLength=None,
                maxLength=None,
            ),
        )
        count += 1

Worksheet names are required to be in Chinese without user opt-in.

Low
Category
Output Handling
Confidence
99% confidence
Finding

The worksheet-naming rule explicitly requires Chinese names rather than merely providing Chinese examples. The file offers no language choice or justification for imposing this requirement regardless of the user's preferred language.

Content

No source excerpt is available for this finding.