pentest-agent-vs-llm-benchmark-effectiveness_A34DF1A1-2F25-5439-9D41-0DCBBBB34A45

{
    "lastseen": "2026-06-25T16:38:41",
    "description": "Backbone or Backbone-Architecture? A controlled study of LLM agents on web-penetration-testing CTFs. The scaffold around the model often decides more than the model does \u2014 and we measured exactly how much. --- Most \"agentic pentest\" leaderboards report...",
    "published": "2026-06-25T15:04:29",
    "modified": "2026-06-25T16:31:33",
    "type": "githubexploit",
    "title": "pentest-agent-vs-llm-benchmark-effectiveness",
    "source": "",
    "references": "",
    "id": "A34DF1A1-2F25-5439-9D41-0DCBBBB34A45",
    "bulletinFamily": "exploit",
    "cwe": null,
    "cvelist": [],
    "sourceData": "",
    "sourceHref": "",
    "cvss": {
        "score": 0,
        "severity": "NONE",
        "vector": "NONE",
        "version": "NONE"
    },
    "cvss2": [],
    "cvss3": {
        "version": "",
        "vectorString": "",
        "baseScore": 0,
        "baseSeverity": "",
        "attackVector": "",
        "attackComplexity": "",
        "privilegesRequired": "",
        "userInteraction": "",
        "scope": "",
        "confidentialityImpact": "",
        "integrityImpact": "",
        "availabilityImpact": "",
        "cvssV3": {
            "version": "",
            "vectorString": "",
            "baseScore": 0,
            "baseSeverity": "",
            "attackVector": "",
            "attackComplexity": "",
            "privilegesRequired": "",
            "userInteraction": "",
            "scope": "",
            "confidentialityImpact": "",
            "integrityImpact": "",
            "availabilityImpact": ""
        }
    },
    "href": "https://github.com/ZeeshanSultan/pentest-agent-vs-llm-benchmark-effectiveness",
    "category_name": "Exploit",
    "post_link": "",
    "product": "",
    "version": "",
    "vendor": "",
    "ai_description": "",
    "ai_severity": "",
    "ai_vendor": "",
    "ai_product": "",
    "ai_version": "",
    "ai_score": 0
}