skills/openclaw/skills/camoufox/Gen Agent Trust Hub

camoufox

Warn

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's installation script scripts/setup.sh uses sudo to install system packages such as python3-venv, python3-full, and xvfb. This behavior requires root access and poses a risk if the script logic is compromised.
  • [EXTERNAL_DOWNLOADS]: During setup, the skill fetches the camoufox library from the Python Package Index (PyPI) and system utilities from official Linux package repositories. These references target well-known and standard software registries.
  • [PROMPT_INJECTION]: The scripts scripts/browse.py and scripts/login_session.py accept arbitrary URLs, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Untrusted data enters the system whenever the browser navigates to an external URL and retrieves page text or screenshots.
  • Boundary markers: No delimiters or explicit instructions are provided to the agent to ignore or isolate instructions found within the retrieved web content.
  • Capability inventory: The skill enables full browser navigation, page interaction, text extraction, and screenshot capture.
  • Sanitization: The page content is extracted using inner_text('body') and returned to the agent without filtering or sanitizing potential malicious instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 06:21 AM