codex-slides-browser

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local Node.js script (../codex-slides/scripts/codex-slides.mjs) to open slide projects and handle browser handoff. This is a functional requirement that leverages internal system scripts rather than external or untrusted code.
  • [PROMPT_INJECTION]: The CLI instruction incorporates user-controlled data via the <input> variable into a shell command. Ingestion points: User-provided deck names and view parameters. Boundary markers: The variable is enclosed in single quotes. Capability inventory: Execution of local scripts to manage project states and visual previews. Sanitization: No input validation or escaping procedures are defined to prevent potential command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 04:05 PM
Security Audit — agent-trust-hub — codex-slides-browser