ClawHub
Back to skill

Security audit

不同方位倾斜面辐射量计算

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward local solar-radiation calculator that reads a user-provided Excel file and writes a calculated Excel report.

Install this if you are comfortable running a local Python script on Excel files you provide and receiving Chinese-labeled workbook output. Review the generated output path when invoking it, especially if you do not pass an explicit --output value.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger examples and much of the user-facing output specification assume Chinese-language interaction and labels, but the document does not offer a language choice or explain that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy because users are implicitly required to interact in a specific language.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · scripts/calculate_tilt_radiation.py (reported line 260)May include surrounding context.

python
def write_output_excel(output_path, data, tilt, azimuth, latitude, results):
    """Write calculation results to Excel."""
    wb = openpyxl.Workbook()
    
    title_font = Font(bold=True, size=14, color="FFFFFF")

Static analysis

No suspicious patterns detected.