wp-project-triage
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill provides an indirect prompt injection surface by reading and processing the contents of arbitrary files within the repository (e.g., package.json, PHP headers).
- Ingestion points: scripts/detect_wp_project.mjs via readFileSafe and scanForTokens.
- Boundary markers: Absent (raw JSON output).
- Capability inventory: Limited to filesystem read and stdout; no subprocess or network capabilities.
- Sanitization: Absent; content is stringified directly into the report.
- [SAFE]: The script performs filesystem-bound discovery of WordPress project configurations and tooling. It limits file reads to a maximum size and specifically targets non-sensitive constants (such as WP_DEBUG and SAVEQUERIES) for status checking rather than extracting credentials or secrets.
Audit Metadata