Code Review & Testing · IN-DEPTH PROFILE

semgrep

Approval-gated Semgrep security scans with telemetry disabled and auditable SARIF output.

View listed source ↗Installation guide ↓
Best for

Security teams needing a controlled first-pass code scan

What you get

Plan the scan + Approve exact rulesets

Main limitation

Requires Semgrep and network access for registry or third-party rules; Pro-only cross-file analysis may be unavailable.

First risk

Third-party rules and source exposure. The workflow may clone external rules and optional engines can communicate with services. Review the plan, keep metrics off, and do not scan sensitive code with unapproved network access.

EVIDENCE FRESHNESS

Three checks, kept separate

A recent source check is not a runtime test or security audit.

Upstream sourceChecked 2026-08-20

Pinned revision · 9b281335

Open pinned commit ↗
SkillSignal profileEditorial metadata

Updated 2026-08-20

Runtime & securityNot independently verified

Source review does not certify behavior or safety.

30-SECOND BRIEF

What it does—and when it fits

Semgrep is Trail of Bits' approval-gated security scan workflow. It detects languages, proposes exact official and third-party rulesets, disables telemetry, runs approved scans in batches, and merges auditable results into SARIF while recording failures and skipped coverage.

INSTALL BY AGENT

Choose your Agent

Paths come from official Agent docs or the universal installer behind skills.sh. Compatibility still follows this Skill's record.

Native

This Skill's current record explicitly names this Agent. Still inspect scripts, permissions, and external dependencies first.

Project scope.claude/skills/semgrep/
Personal scope~/.claude/skills/semgrep/

Use project scope for team sharing and personal scope across repositories. The installer defaults to project scope; add -g for personal scope.

Install command (project scope)npx skills add trailofbits/skills --skill semgrep --agent claude-code
Official agent docs

Claude Code discovers custom Skill folders automatically at project or personal scope.

View path evidence ↗

TYPICAL WORKFLOW

A practical workflow

01

Plan the scan

Detect languages and choose full or important-only coverage.

02

Approve exact rulesets

Show target, engine, mode, and every ruleset before execution.

03

Merge auditable output

Preserve raw scans and report failed, skipped, or empty coverage.

THE TRADEOFFS

Advantages and tradeoffs

Notable strengths

  1. Telemetry-off commands and an explicit plan reduce accidental source disclosure.
  2. Combines fast multi-language rules with optional cross-file Pro analysis.

Limitations

  1. Requires Semgrep and network access for registry or third-party rules; Pro-only cross-file analysis may be unavailable.
  2. Ruleset coverage is not proof of application security and partial failures can create blind spots.

COMPARE THE TRADEOFF

Consider these close alternatives

These are deterministic nearby candidates, not paid placements or a universal ranking. Open the full profile before choosing.

01

Same job family · native to Claude Code

frontend-design

Design constraints that push generated interfaces beyond generic AI UI.
Tradeoff to check
Aesthetic judgments remain subjective and still need stakeholder review.
First risk
Style over function · Medium
Source state
Pinned · 0a64e398
Open profile ↗
02

Same job family · native to Claude Code

mcp-builder

Plan, implement, and evaluate high-quality MCP servers in Python or TypeScript.
Tradeoff to check
The guide cannot replace current MCP SDK or target-API documentation.
First risk
Overpowered external-service tools · High
Source state
Pinned · 0a64e398
Open profile ↗
03

Same job family · native to Claude Code

skill-creator

Create, improve, and benchmark Agent Skills with trigger tests and comparative evaluation.
Tradeoff to check
Meaningful benchmarks require representative prompts, repeat runs, and careful human judgment.
First risk
Untrusted evaluation prompts and artifacts · High
Source state
Pinned · 0a64e398
Open profile ↗
Compare more in the directory →

BEST FIT

Who it is for

→

Security teams needing a controlled first-pass code scan

→

Developers producing reviewable SARIF before code review

BEFORE YOU USE IT

Risks to review before use

High

Third-party rules and source exposure

The workflow may clone external rules and optional engines can communicate with services. Review the plan, keep metrics off, and do not scan sensitive code with unapproved network access.

SECURITY

What the permission profile means

  • Verify every command retains --metrics=off and the approved target scope.
  • Report failed and skipped rulesets instead of presenting a partial scan as clean.

Not a security certification. External ratings are attributed references. SkillSignal has not independently executed or security-reviewed this Skill.

INSIDE THE PACKAGE

Indexed files

SKILL.mdUpstream package contentSource-linked
workflows/Upstream package contentSource-linked
references/Upstream package contentSource-linked
scripts/Upstream package contentSource-linked

TAGS

semgrepsecurity-scansarif

Original SkillSignal editorial profile grounded in Trail of Bits commit 9b281335, checked 2026-08-20; not independently executed or security-certified.