wp-gravityview
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill documents an attack surface for indirect prompt injection where malicious instructions could be embedded in the data the skill processes.
- Ingestion points: Gravity Forms entries, which constitute untrusted external data, are the primary input for the Views described in the skill and the AI classification workflows.
- Boundary markers: The provided instructions do not define explicit boundary markers or delimiters to separate untrusted entry data from agent instructions during processing.
- Capability inventory: The skill facilitates front-end data display, entry approval workflows via Gravity Connect, and the export of View configurations for LLM prototyping.
- Sanitization: The skill provides a corrective PHP filter implementation (
gravityview/fields/custom/content_after) to mask sensitive field content like API keys, which mitigates simple exposure but does not fully address adversarial injection content within other entry fields.
Audit Metadata