Skills
Navigate
skills/steveclarke/dotfiles/electron/Gen Agent Trust Hub

electron

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from untrusted sources (desktop application UI and content), making it vulnerable to indirect prompt injection.
  • Ingestion points: Data is pulled from application windows using agent-browser snapshot and agent-browser get text (SKILL.md, electron/SKILL.md).
  • Boundary markers: No delimiters or protective instructions are provided to separate application content from system instructions.
  • Capability inventory: The skill enables high-privilege interactions via agent-browser click, fill, and keyboard type (SKILL.md).
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the applications.
  • [COMMAND_EXECUTION]: The skill provides commands to launch desktop applications with remote debugging enabled, allowing for programmatic control of application instances.
  • Evidence: Usage of open -a on macOS and direct execution on Linux/Windows with the --remote-debugging-port flag (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 01:51 AM