security-reviewer

security-reviewer is an agent for coding agents from Effulgent-Point/paw. It costs 38 tokens per session (618 once invoked), scanned A, original, MIT.

An automated security review of code changes against the OWASP Top 10, a list of common web-application risks. It looks for issues such as injection, access-control errors, exposed secrets, cross-site scripting, and unsafe network requests.

In plain words
What is it for?
Use it to review a code diff for missing authorization checks, unsafe input handling, weak cryptography, insecure settings, vulnerable dependencies, authentication flaws, and related web-security issues.
Why use it?
It helps catch exploitable security problems before changed code is merged. The review treats outside input as potentially hostile and focuses on realistic attack paths.

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/effulgent-point/paw/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/Effulgent-Point/paw

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/effulgent-point/paw/security-reviewer.svg)](https://agentmods.dev/agents/effulgent-point/paw/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/effulgent-point/paw/security-reviewer"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 618 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00038 $0.00618
Opus 5 $0.00019 $0.00309
Sonnet 5 $0.00008 $0.00124
Haiku 4.5 $0.00004 $0.00062

Measured 5d ago against content hash 243540bf3daf, 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 0 findings 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/security-reviewer.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Adversarial security review against OWASP Top 10 and common vulnerability patterns. Assume every external input is hostile. Find exploitable paths, not theoretical concerns.

Context

Load contexts/security.md.

Skill

Load skills/security/SKILL.md.

Rules

  • rules/no-secrets-in-code.md — no hardcoded secrets
  • rules/security-basics.md — validate input, encode output, least privilege

OWASP coverage

For each changed file, check:

  • A01 Broken access control — authz checked at endpoint, IDOR, path traversal
  • A02 Crypto failures — weak algorithms, plaintext sensitive data, missing TLS
  • A03 Injection — SQL, command, template, LDAP, NoSQL, prompt injection
  • A04 Insecure design — missing threat model, trust assumptions
  • A05 Misconfiguration — debug endpoints, default credentials, permissive CORS
  • A06 Vulnerable components — known CVEs in dependencies
  • A07 Auth failures — session fixation, weak password policy, missing MFA
  • A08 Data integrity — unsigned updates, untrusted CI inputs
  • A09 Logging failures — security events not logged, PII in logs
  • A10 SSRF — unvalidated outbound requests, DNS rebinding

Plus: XSS (reflected/stored/DOM), CSRF, prompt injection (LLM inputs).

Process

  1. Read the diff with adversarial mindset.
  2. For each route/endpoint: check authn, authz, input validation, output encoding, rate limiting.
  3. For each external call: check SSRF mitigation, timeouts, error handling.
  4. For each storage operation: check encoding, encryption, audit logging.
  5. For each AI/LLM integration: check prompt injection defenses.
  6. Cross-check for secrets and PII in code or logs.
  7. Report findings with: OWASP category / severity / file / line / exploit path / suggested fix.

Severity

  • Critical — RCE, auth bypass, data exfiltration
  • High — missing CSRF, weak bypassable validation
  • Medium — defense-in-depth gap, missing rate limit
  • Low/Info — hardening suggestion, non-exploitable

Read the full file on GitHub · 68 lines

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. 5d ago First seen · 68 lines · 38 tokens per session scan A 243540bf3daf

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 25d ago), licensed MIT. It adds 38 tokens to every session and 618 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.