ats_detect_adversarial
Scans CVs for adversarial content: prompt injection, hidden text, and keyword stuffing to protect AI screening from manipulation.
Instructions
Detect adversarial tactics embedded in a submitted CV (spec §2).
Scans the CV file for three classes of adversarial content:
prompt_injection (CRITICAL): screener-directed imperatives in the text (EN + FR) designed to manipulate AI screeners.
hidden_text (CRITICAL): near-invisible text via white/near-white colour or sub-4pt font size (PDF and DOCX).
keyword_stuffing (HIGH): anomalous token or line repetition designed to game keyword-match scoring.
This tool ONLY detects adversarial content — it never produces it.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"cv_path": "<cv_path>"
},
"name": "ats_detect_adversarial"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cv_path | Yes | Absolute path to the CV file (PDF, DOCX, TXT, or MD). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |