Security Auditor

What it does

When your agent uses it

• Auditing a codebase for SQL injection, XSS or command injection
• Finding hardcoded API keys and credentials before a release
• Checking config files and dependencies for insecure defaults or known CVEs
• Producing a security report for a project

Example prompts

• “Run a security audit on this repo and list the highest-risk findings.”
• “Scan the project for hardcoded secrets and committed .env files.”
• “Check our dependencies for known CVEs and tell me what to upgrade.”
• “Review the login and session code against the OWASP Top 10.”

Requirements

• Python, to run the scan scripts

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Reconnaissance
2. 2Secrets Detection
3. 3Vulnerability Scanning
4. 4Dependency Audit
5. 5Configuration Review
6. 6Authentication and Authorization Review

What it can do on your machine

Read from SKILL.md and the folder at commit 9c76fba. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • pip
  • npm
  • npx
  • trivy

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

• Network

  No URLs in SKILL.md. Its commands use pip, npm and npx, which can reach the network depending on how they are called.

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • SECRET_KEY

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

Context cost

Security Auditor loads about 1.8k tokens when it runs, and up to ~4.7k if it reads all its reference files. Until then it costs about 142 tokens; SKILL.md has 418 words of instructions outside code blocks.

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

~142

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

~4.7k

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

• NoteMentions a .env fileSKILL.md:61

  - `.env` files or config files with plaintext secrets

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); the scripts in this folder are not scanned.

SKILL.md

The full file from eigent-ai/eigent at commit 9c76fba, republished under its Apache-2.0 licence (© eigent-ai). 418 words, ~1,804 tokens.

name

skill-security-auditor

description

Security auditing for code, configs, and infrastructure. Use when the user wants to audit or improve security: scan for vulnerabilities (SQL injection, XSS, command injection, path traversal), detect hardcoded secrets and credentials, review auth and authorization, check dependencies for known CVEs, audit config files for insecure defaults, or generate security reports. Trigger on "security audit", "vulnerability scan", "code review for security", "find secrets", "check for vulnerabilities", "OWASP", "CVE", or questions about code security.

license

Complete terms in LICENSE.txt

python scripts/scan_project.py /path/to/project

python scripts/scan_project.py /path/to/some/project --format text
python scripts/scan_secrets.py /path/to/some/project --format text

# Identify languages, frameworks, and entry points
find . -type f -name "*.py" -o -name "*.js" -o -name "*.ts" -o -name "*.go" -o -name "*.java" | head -20
cat package.json pyproject.toml requirements.txt go.mod pom.xml 2>/dev/null

python scripts/scan_secrets.py /path/to/project

# Dangerous: SQL injection
cursor.execute(f"SELECT * FROM users WHERE id = {user_id}")
# Safe: Parameterized query
cursor.execute("SELECT * FROM users WHERE id = %s", (user_id,))

# Dangerous: Command injection
os.system(f"ping {hostname}")
# Safe: Use subprocess with list args
subprocess.run(["ping", hostname], capture_output=True)

# Dangerous: Path traversal
open(f"/data/{user_input}")
# Safe: Validate and resolve path
path = pathlib.Path("/data") / user_input
path.resolve().relative_to(pathlib.Path("/data").resolve())

// Dangerous: XSS via innerHTML
element.innerHTML = userInput;
// Safe: Use textContent or sanitize
element.textContent = userInput;

// Dangerous: Prototype pollution
Object.assign(target, JSON.parse(userInput));
// Safe: Validate input structure
const parsed = JSON.parse(userInput);
if (typeof parsed !== 'object' || Array.isArray(parsed)) throw new Error();
const sanitized = Object.fromEntries(
  Object.entries(parsed).filter(([k]) => !k.startsWith('__'))
);

// Dangerous: eval or Function constructor
eval(userInput);
// Safe: Never use eval with user input

// Dangerous: SQL injection
db.Query("SELECT * FROM users WHERE id = " + id)
// Safe: Parameterized query
db.Query("SELECT * FROM users WHERE id = $1", id)

// Dangerous: Path traversal
http.ServeFile(w, r, filepath.Join(baseDir, r.URL.Path))
// Safe: Clean and validate path
cleaned := filepath.Clean(r.URL.Path)
full := filepath.Join(baseDir, cleaned)
if !strings.HasPrefix(full, baseDir) { http.Error(...) }

# Python
pip audit
safety check -r requirements.txt

# Node.js
npm audit
npx auditjs ossi

# Go
govulncheck ./...

# General (if Trivy is available)
trivy fs --scanners vuln /path/to/project

# Common misconfigurations to flag:
DEBUG: true                    # Debug mode in production
ALLOWED_HOSTS: ["*"]          # Unrestricted host access
CORS_ALLOW_ALL_ORIGINS: true  # Open CORS policy
SECRET_KEY: "default"         # Default or weak secret key
SSL_VERIFY: false             # Disabled TLS verification

# Security Audit Report

## Summary
- **Project**: [name]
- **Date**: [date]
- **Scope**: [what was audited]
- **Risk Level**: [Critical/High/Medium/Low]

## Findings

### [SEVERITY] Finding Title
- **Category**: [OWASP category]
- **Location**: [file:line]
- **Description**: [what the issue is]
- **Impact**: [what could happen if exploited]
- **Recommendation**: [how to fix]

## Statistics
- Total findings: [count]
- Critical: [count] | High: [count] | Medium: [count] | Low: [count]

© eigent-ai, Apache-2.0. 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 5 other files (scripts, references) in resources/example-skills/skill-security-auditor of eigent-ai/eigent.

• SKILL.md
• LICENSE.txt
• references/secrets-patterns.md
• references/vulnerability-patterns.md
• scripts/scan_project.py
• scripts/scan_secrets.py

Open the folder on GitHubat commit 9c76fba