Challenge
A narrow signature can miss variants, while a broad static rule can flood the researcher with false positives. The useful result is a short, traceable lead list that still requires manual validation.
Project case study
An LLM-assisted variant-analysis engine that validates and ranks static-analysis matches into a short list of manually-verifiable leads.
Context
A narrow signature can miss variants, while a broad static rule can flood the researcher with false positives. The useful result is a short, traceable lead list that still requires manual validation.
Separate broad detection from validation. Semgrep gathers candidates, provenance-aware heuristics remove obvious noise, an optional LLM pass helps rank the remainder, and the researcher makes every security decision.
Designed and built the detection, heuristic validation, optional LLM triage, benchmark, CI-tested workflow, and kameReport-compatible export path.
In a documented seven-case experiment, the broader rule surfaced six candidate patterns instead of none. Each output remains an unverified lead.
How it works
Translate a known weakness into a deliberately broad source signature.
Use Semgrep to find code that may share the relevant data-flow shape.
Apply provenance-aware heuristics and optional LLM ranking.
Review the short list and confirm behavior outside the tool.
Evidence and limits
CyberKareem/kameHuntSource snapshot at commit 6a6eac1123a02d150945878a798c47e8af752963. Later repository changes are outside this case study.
Inspect pinned revision opens in a new tab