dogear

enter for all results · esc to close

Where the LLM Stops: Deterministic Scoring in an AI-Assisted VAPT Pipeline

aayushyadav.hashnode.devsite

visit aayushyadav.hashnode.dev ↗
0
sign in to dogear this
from
Web Security
added
2026-10-10
likes
0

similar

  1. ai-evaluation github.com
    tool category #datascience link ↗

    Open-source LLM and agent evaluation framework with 50+ metrics, LLM-as-Judge augmentation, and guardrail scanners (jailbreak, PII, prompt-injection). Useful for scoring RAG outputs, agent trajectories, and function-calling behavior in data-science workflows.

  2. LLM Stats llm-stats.com
    site category #generative-ai link ↗

    Compare AI models across benchmarks, pricing, speed, and context window.

  3. AI/LLM Exploitation Challenges academy.8ksec.io
    site category #prompt-injection link ↗

    AI, ML, and LLMs CTF Challenges.

  4. OWASP GenAI LLM Top 10 (2026) genai.owasp.org
    site category #prompt-injection link ↗

    The canonical community reference for LLM application risk, with prompt injection at number one. Supersedes the 2025 edition; the per-risk 2025 pages remain online as an archive.

  5. OWASP Top 10 for LLM Applications genai.owasp.org
    site category #artificial-intelligence link ↗

    Risks and mitigations for developing and deploying generative AI applications.

  6. vLLM docs.vllm.ai
    site category #artificial-intelligence link ↗

    An inference and serving engine for language models.

Web Security › Practices > Application: “Technical write-up on designing an AI-assisted VAPT pipeline with deterministic CVSS scoring, passive confidence verification, and LLM-generated vulnerability explanations and remediation.”