Performing security code review
Skill jeremylongshore/claude-code-plugins-plus-skills/skills/.curated/performing-security-code-review
'Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin. it analyzes code for potential vulnerabilities like sql injection, xss, authentication flaws, and insecure dependencies. AI assistant uses this skill wh... Use when assessing security or running audits. Trigger with phrases like ''security scan'', ''audit'', or ''vulnerability''.From its SKILL.md
npx -y skills add jeremylongshore/claude-code-plugins-plus-skills --skill performing-security-code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
5.3 KB, 923 tokens by cl100k_base, as published. Nobody here has run it
Performing Security Code Review
Overview
Conducts security-focused code reviews by scanning source files for common vulnerability patterns including SQL injection, XSS, authentication flaws, insecure dependencies, and secret exposure. Produces structured severity-rated reports with specific remediation guidance.
Prerequisites
- Read access to all source files in the target project
grepavailable on PATH for pattern matching- Access to
package.jsonor equivalent dependency manifest for dependency auditing - Familiarity with OWASP Top 10 vulnerability categories
Instructions
- Identify the scope of the review: specific files, directories, or the entire codebase. Confirm the primary language(s) and framework(s) in use.
- Scan for hardcoded secrets and credentials:
- Search for patterns matching API keys, tokens, passwords, AWS access keys (
AKIA...), and private key headers (BEGIN PRIVATE KEY). - Flag any
.envfiles or configuration files containing plaintext secrets.
- Search for patterns matching API keys, tokens, passwords, AWS access keys (
- Analyze code for injection vulnerabilities:
- Identify raw SQL string concatenation (SQL injection risk).
- Locate unsanitized user input rendered in HTML (XSS risk).
- Check for
eval(),exec(), orFunction()calls with dynamic input (code injection risk).
- Review authentication and authorization logic:
- Verify password hashing uses strong algorithms (bcrypt, argon2) rather than MD5/SHA1.
- Check for missing authentication on sensitive endpoints.
- Identify overly permissive CORS configurations.
- Audit dependencies for known vulnerabilities:
- Run
npm auditor equivalent package manager audit command. - Cross-reference dependency versions against known CVE databases.
- Run
- Check for insecure communication patterns:
- Flag HTTP URLs where HTTPS is expected.
- Identify disabled TLS certificate verification.
- Compile findings into a structured report sorted by severity (Critical, High, Medium, Low), including the vulnerable code location, explanation, and remediation steps.
Output
A structured security review report containing:
- Summary with total findings count by severity level
- Per-finding entries with: file path, line number, vulnerability type, severity, code snippet, explanation, and recommended fix
- Dependency audit results with CVE identifiers where applicable
- Overall risk assessment (Critical / High / Medium / Low / Clean)
Error Handling
| Error | Cause | Solution |
|---|---|---|
| No source files found | Incorrect scope path or empty directory | Verify the target directory path and confirm it contains source files |
| Binary files in scan | Non-text files matched by search patterns | Exclude binary extensions and node_modules/ from scans |
| Dependency manifest missing | No package.json, requirements.txt, or equivalent | Skip dependency audit; note in report that dependency analysis was not possible |
| Permission denied on files | Restricted file access | Request read permissions or narrow the review scope to accessible files |
| False positive on secret pattern | Benign string matching secret regex | Verify context before reporting; mark as potential false positive if the match appears in test fixtures or documentation |
Examples
SQL injection review:
Trigger: "Review this database query code for SQL injection vulnerabilities."
Process: Scan all files containing SQL query construction. Identify string concatenation with user input ("SELECT * FROM users WHERE id = " + userId). Report as High severity with remediation: use parameterized queries or prepared statements.
Dependency vulnerability scan:
Trigger: "Check this project's dependencies for known security vulnerabilities."
Process: Run npm audit on the project. Parse output for vulnerabilities. Report each finding with CVE identifier, affected package, installed version, and patched version. Recommend npm audit fix or manual version pinning.
Full codebase security audit: Trigger: "Run a security scan on this codebase." Process: Execute all seven scan categories (secrets, injection, auth, dependencies, communication, dangerous commands, obfuscation). Produce a comprehensive report with findings grouped by category and sorted by severity.
Resources
- OWASP Top 10 -- industry-standard vulnerability classification
- Node.js Security Checklist -- Node-specific security guidance
- CWE/SANS Top 25 -- most dangerous software weaknesses
${CLAUDE_SKILL_DIR}/references/README.md-- bundled reference materials
What ships with it: 7 files
23.9 KB alongside SKILL.md, 3 of them executable
assets/
- example_code_secure.pyruns7.1 KB
- example_code_vulnerable.pyruns6.1 KB
- README.md424 B
- report_template.md5.2 KB
references/
- README.md57 B
scripts/
- code_analyzer.pyruns4.7 KB
- README.md448 B
Gives 0 of the 12 instructions most code review skills give in 923 tokens
Counted across 668 of the 814 authors here whose files we hold, read 2026-09-06
- Provide technical reasoning when pushing backin 84 of 668, across 70 files
- Fix critical issues immediatelyin 77 of 668, across 60 files
- Dispatch a code reviewer subagentin 76 of 668, across 59 files
- Fix important issues before proceedingin 73 of 668, across 56 files
- Ask for clarification on unclear itemsin 68 of 668, across 56 files
- Verify feedback against codebase before implementationin 66 of 668, across 55 files
- Implement fixes one at a timein 64 of 668, across 53 files
- Test each fix individuallyin 62 of 668, across 51 files
- Restate technical requirements in own wordsin 57 of 668, across 46 files
- Reply to inline comments in the specific threadin 51 of 668, across 40 files
- Note minor issues for laterin 49 of 668, across 34 files
- Group findings by severityin 48 of 668, across 47 files
Said here and by no other author read
- identify the scope of the review
- check for insecure communication patterns
- exclude binary files and dependency folders from scans
- verify context before reporting potential false positives
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.