Semgrep Rule Creator

What it does

When your agent uses it

• Writing Semgrep rules
• Building custom static analysis detections

Example prompts

• “Use the semgrep-rule-creator skill to create custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns”
• “/semgrep-rule-creator”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Glob, Grep, WebFetch

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Rule Syntax
2. 2Pattern Syntax
3. 3Testing Rules
4. 4Taint analysis
5. 5Advanced techniques for taint analysis
6. 6Constant propagation
7. 7Trail of Bits Testing Handbook - Semgrep chapter

What it can do on your machine

Read from SKILL.md and the folder at commit 82fe822. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write
  • Edit
  • Glob
  • Grep
  • WebFetch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • semgrep

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • raw.githubusercontent.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Semgrep Rule Creator loads about 1.8k tokens when it runs, and up to ~5.2k if it reads all its reference files. Until then it costs about 50 tokens; SKILL.md has 619 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~50

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write, Edit, Glob, Grep, WebFetch

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from trailofbits/skills at commit 82fe822, republished under its CC-BY-SA-4.0 licence (© trailofbits). 619 words, ~1,823 tokens.

name

semgrep-rule-creator

description

Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.

allowed-tools

Bash, Read, Write, Edit, Glob, Grep, WebFetch

# BAD: Matches any function call
pattern: $FUNC(...)

# GOOD: Specific dangerous function
pattern: eval(...)

# BAD: Only tests vulnerable case
# ruleid: my-rule
dangerous(user_input)

# GOOD: Include safe cases to verify no false positives
# ruleid: my-rule
dangerous(user_input)

# ok: my-rule
dangerous(sanitize(user_input))

# ok: my-rule
dangerous("hardcoded_safe_value")

# BAD: Only matches exact format
pattern: os.system("rm " + $VAR)

# GOOD: Matches all os.system calls with taint tracking
mode: taint
pattern-sources:
  - pattern: input(...)
pattern-sinks:
  - pattern: os.system(...)

<rule-id>/
├── <rule-id>.yaml     # Semgrep rule
└── <rule-id>.<ext>    # Test file with ruleid/ok annotations

rules:
  - id: insecure-eval
    languages: [python]
    severity: HIGH
    message: User input passed to eval() allows code execution
    mode: taint
    pattern-sources:
      - pattern: request.args.get(...)
    pattern-sinks:
      - pattern: eval(...)

# ruleid: insecure-eval
eval(request.args.get('code'))

# ok: insecure-eval
eval("print('safe')")

Semgrep Rule Progress:
- [ ] Step 1: Analyze the Problem
- [ ] Step 2: Write Tests First
- [ ] Step 3: Analyze AST structure
- [ ] Step 4: Write the rule
- [ ] Step 5: Iterate until all tests pass (semgrep --test)
- [ ] Step 6: Optimize the rule (remove redundancies, re-test)
- [ ] Step 7: Final Run

© trailofbits, CC-BY-SA-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references, assets) in plugins/semgrep-rule-creator/skills/semgrep-rule-creator of trailofbits/skills.

• SKILL.md
• agents/openai.yaml
• assets/trail-of-bits-mark.svg
• references/quick-reference.md
• references/workflow.md

Open the folder on GitHubat commit 82fe822

Used in 6 other repositories

We found 15 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 6 other GitHub owners. This page covers the copy in trailofbits/skills, which our catalogue first saw on October 7, 2026.

• waybarrios/opencode-power-packskills/semgrep-rule-creator
• vigolium/pioliumskills/semgrep-rule-creator
• CraftOS-dev/CraftBotskills/semgrep-rule-creator
• sickn33/agentic-awesome-skillsskills/semgrep-rule-creatorplugins/agentic-awesome-skills/skills/semgrep-rule-creator+1 more
• lingxling/awesome-skills-cnantigravity-awesome-skills/skills/semgrep-rule-creatorantigravity-awesome-skills/plugins/agentic-awesome-skills/skills/semgrep-rule-creator+1 more
• henryalouf/ruflow.agents/skills/semgrep-rule-creator.agents/skills/antigravity-awesome-skills/skills/semgrep-rule-creator+4 more