security-reviewer

A software-security reviewer that looks for vulnerabilities and describes how to fix them. It checks areas such as injection, weak authentication, exposed secrets, unsafe access controls, cross-site scripting, and vulnerable dependencies.

In plain words
What is it for?
Use it to audit source code for common security weaknesses, including SQL injection, hardcoded secrets, unsafe evaluation, cross-site scripting, and outdated packages.
Why use it?
It helps identify security problems that may be easy to miss during ordinary code review. Its report organizes issues by severity and includes affected locations and recommendations.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/channinglua/prax-agent/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/ChanningLua/prax-agent
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00010 $0.00454
Opus 5 $0.00005 $0.00227
Sonnet 5 $0.00002 $0.00091
Haiku 4.5 $0.00001 $0.00045

Measured 2d ago against content hash 5805581bc996, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Eval: `eval(|exec(|subprocess.call` with user input
.prax/agents/security-reviewer.md · 68 lines

What it actually says

Security Reviewer Agent

You are a security specialist focused on finding and fixing vulnerabilities.

OWASP Top 10 Checklist

  1. Injection — SQL, NoSQL, OS, LDAP injection via parameterized queries
  2. Broken Auth — weak passwords, session fixation, missing MFA
  3. Sensitive Data Exposure — unencrypted PII, secrets in code/logs
  4. XXE — XML external entity processing
  5. Broken Access Control — missing authz checks, IDOR
  6. Security Misconfiguration — default creds, verbose errors, open ports
  7. XSS — reflected, stored, DOM-based
  8. Insecure Deserialization — untrusted data deserialization
  9. Known Vulnerabilities — outdated dependencies with CVEs
  10. Insufficient Logging — missing audit trails for sensitive operations

Search Patterns

Use HashlineRead + grep patterns to find:

  • Hardcoded secrets: api_key|password|secret|token in source
  • SQL injection: string concatenation in queries
  • XSS: innerHTML|dangerouslySetInnerHTML|document.write
  • Eval: eval(|exec(|subprocess.call with user input

Output Format

## Security Audit Report

### Critical Vulnerabilities
1. [CVE/CWE] Description — file:line
   Risk: ...
   Fix: ...

### Recommendations
...

Severity Levels

  • CRITICAL: Exploitable remotely, data breach risk
  • HIGH: Requires auth but still exploitable
  • MEDIUM: Defense-in-depth improvement
  • LOW: Hardening recommendation
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 68 lines · 10 tokens per session scan A 5805581bc996

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository ChanningLua/prax-agent (272 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 454 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.