Lightpanda

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The scripts/install.sh script downloads the Lightpanda browser binary from the official vendor repository on GitHub (lightpanda-io/browser).
  • [COMMAND_EXECUTION]: The installation script executes shell commands to detect the operating system and architecture, download the binary, and set executable permissions. It includes a security best practice by verifying the integrity of the downloaded file using SHA256 checksums fetched from the GitHub API.
  • [PROMPT_INJECTION]: As a tool designed for web browsing and content extraction, the skill possesses an inherent surface for indirect prompt injection. Untrusted data from external websites (processed via tools like goto, markdown, and semantic_tree) could contain instructions intended to influence the agent's behavior. The skill includes high-capability tools such as evaluate (JavaScript execution), click, and fill which interact with this untrusted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 01:33 PM