ClawHub
Back to skill

Security audit

Newspaper Brief

Security checks for vulnerabilities and agentic risk

Overview

This skill locally turns user-provided notes or summaries into a newspaper-style HTML/PNG brief, with no evidence of hidden data access, persistence, or remote execution.

Install if you want a local HTML/PNG newspaper-brief renderer. Be aware it processes the content you provide into output files, and PNG export may launch a local browser; only use trusted input/output paths and do not set NEWSPAPER_BRIEF_BROWSER to an untrusted program.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

This JSON sample is entirely Chinese-language content, including the paper name, title, headings, and footer, with no indication that language is configurable or that the artifact is intentionally region-specific. Under the stated policy, natural-language content that imposes a language without opt-in can be a locale-policy violation.

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/render_newspaper.py (reported line 503)May include surrounding context.

python
file_url,
    ]
    try:
        proc = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
        if proc.returncode == 0 and png_path.exists():
            cropped_ok, crop_msg = crop_bottom_whitespace(png_path)
            if cropped_ok:

Static analysis

No suspicious patterns detected.