← Browse

@lowyshin/security-scan

A

Performs a rapid security sweep for secrets, API keys, and common vulnerabilities using cross-platform platform tools.

skillclaude

Install

agr install @lowyshin/security-scan --target claude

Writes 1 file into .claude/skills/, pinned to git-a24e6265.

  • .claude/skills/security-scan/SKILL.md

Document


name: security-scan description: Performs a rapid security sweep for secrets, API keys, and common vulnerabilities using cross-platform platform tools. triggers: security scan, 보안 점검, 취약점 점검, scan for secrets, check keys

security-scan Skill

This skill performs a fast, grep-based security scan of the repository. It focuses on identifying hardcoded secrets and common misconfigurations.

🛠️ Usage

Trigger this skill before any git push or after significant code changes.

Scan Patterns

The following patterns are scanned using the grep_search platform tool:

CategoryPatternDescription
Secretssk-[a-zA-Z0-9]{48}OpenAI API Keys
Secretsghp_[a-zA-Z0-9]{36}GitHub Personal Access Tokens
SecretsAKIA[0-9A-Z]{16}AWS Access Key IDs
Config\.env$Unencrypted environment files
Vulnerabilityeval\(Dangerous eval usage
VulnerabilitydangerouslySetInnerHTMLPotential XSS (React)

💻 Cross-Platform Implementation

This skill uses the platform-native grep_search API, which is optimized for Windows, Mac, and Linux. No extra binary installation (like rg) is required.

Example Scan Execution

// Step 1: Detect current OS (via env-check)
// Step 2: Use grep_search with absolute path
grep_search({
  Query: "sk-[a-zA-Z0-9]{48}",
  SearchPath: "/absolute/path/to/project",
  IsRegex: true
});

🛡️ Response Actions

If a match is found:

  1. Stop: Do not proceed with the task until the vulnerability is addressed.
  2. Alert: Report the exact file and line number to the user.
  3. Fix: Recommend moving the secret to an environment variable or using a secret manager.

Trustgrade A

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • passLicense

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-a24e6265e8832026-07-31