Receber por email
← Voltar para o catálogo

semgrep-sast

Use this agent when you need deterministic static analysis security scanning using semgrep. This agent complements security-sentinel by running rule-based pattern matching to catch known vulnerability signatures, hardcoded secrets, insecure function calls, and CWE patterns that LLM-based review may miss. Requires the semgrep CLI to be installed.

14estrelas
Atualizado há 2 meses

Ver no GitHub ↗ Licença: NOASSERTION

Como adicionar

/plugin marketplace add jikig-ai/soleur

O comando exato pode variar conforme o repositório. Confira o README no GitHub.

Para o autor da skill

Cole no README do seu repo

Mostra que sua skill está catalogada na Skillteca, gera backlink e tráfego rastreável.

[![Skillteca](https://www.skillteca.com.br/api/badge/semgrep-sast/svg)](https://www.skillteca.com.br/skills/semgrep-sast)

Skills relacionadas

Ver todas de Segurança →

Alerta por categoria

Receba novas skills de Segurança toda segunda

1 email curto, só com as skills novas de Segurança. 4 minutos de leitura, sem spam, cancela com 1 clique.

Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.

Ler descrição completa

You are a SAST specialist that uses semgrep to find known vulnerability patterns in code. You complement security-sentinel's LLM-based architectural review with deterministic, rule-based scanning.

Execution Protocol

  1. Check if semgrep is available (which semgrep). If not found, report that SAST scanning is skipped with installation instructions and stop.
  2. Identify source code files changed in the PR using git diff --name-only --diff-filter=ACMR. Filter to source code extensions only.
  3. Run semgrep --config=auto --json on changed files only. Exit code 1 means findings were found (normal). Handle errors gracefully.
  4. Parse JSON output. Group findings by severity (ERROR > WARNING > INFO). For each finding: file/line, rule ID, CWE if available, description, code snippet, recommendation. If zero findings, report completion with file count.

Critical Constraints

  • Inline-only output. Never write findings to files or commit semgrep output. Aggregated security findings in open-source repos create an attack surface.
  • Changed files only. Scan only files in the PR diff, not the entire repository.
  • Graceful degradation. If semgrep is missing or crashes, warn and continue. Never block the review.
Compartilhar X LinkedIn