ClawHub
Back to skill

Security audit

Market Research Reports

Security checks for vulnerabilities and agentic risk

Overview

This skill is a report-generation helper that writes local report files and runs local visualization/LaTeX commands, with no evidence of hidden persistence, credential access, exfiltration, or destructive behavior.

Install only if you want an agent to create local report folders, generate image files, and run local Python/LaTeX tooling. Choose an output directory you are comfortable modifying, verify any generated market data and citations yourself, and note that some referenced template/style assets are missing from this package.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

This code chunk only covers one subset of the declared functionality: generating market-report visuals. It defines core and extended image prompts, selects a target tool, and invokes external scripts to create PNG files. There is no logic for assembling a comprehensive report, no LaTeX generation, no integration with a research retrieval tool, and no analytical engine that computes or writes Porter's, PESTLE, SWOT, TAM/SAM/SOM, or BCG analyses. Some frameworks appear in prompt text for diagrams, but that is materially different from performing the analyses themselves. Therefore the declared description overstates the actual behavior of this code chunk.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/generate_market_visuals.py (reported line 375)May include surrounding context.

python
print(f"        Prompt: {formatted_prompt[:80]}...")
    
    try:
        result = subprocess.run(
            cmd,
            capture_output=True,
            text=True,

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill instructs the agent to create directories, write files, and run shell commands such as Python scripts and LaTeX compilation without explicit user confirmation or safety gating. In an agentic environment with Write, Edit, and Bash enabled, this can cause unintended filesystem modifications and execution of local tooling based solely on natural-language task invocation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

This code creates the output directory and then invokes downstream generator scripts that write image files into it. While the CLI arguments imply output generation, there is no explicit safety warning or confirmation around filesystem modification, and the called tools may overwrite or create many files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.