openai-codex-security
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the
@openai/codex-securitypackage from the npm registry for scanning and vulnerability remediation. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze source code to identify and fix security issues, which presents a surface for indirect prompt injection attacks.
- Ingestion points: Files and directories within the local project targeted by the scan commands (SKILL.md).
- Boundary markers: The documentation does not specify the use of delimiters or provide explicit instructions to ignore directives embedded within the scanned code.
- Capability inventory: Includes reading local files, making network requests for AI processing, and writing files for report generation and automated code fixes (SKILL.md).
- Sanitization: No specific sanitization or validation protocols for the analyzed code content are described in the instructions.
Audit Metadata