security

An application-security review agent that looks for common web security weaknesses, access-control errors, exposed sensitive data, unsafe input handling, and dependency vulnerabilities. It focuses on security risks in the changed code.

In plain words
What is it for?
Use it to review authentication and permissions, personal or financial data, credentials, validation, CORS, security headers, rate limits, and dependencies with known CVEs. It does not review general code quality or database performance.
Why use it?
It helps find ways an attacker could misuse the application before those weaknesses reach production.

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/ggemba/squad-mcp/security
Clone the repo
git clone --depth 1 https://github.com/ggemba/squad-mcp
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,756 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 $0.00031 $0.01756
Opus 5 $0.00015 $0.00878
Sonnet 5 $0.00006 $0.00351
Haiku 4.5 $0.00003 $0.00176

Measured 2d ago against content hash 120da59116d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security 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 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.

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.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security

Reference: Severity and Ownership Matrix

Role

Application security specialist. Identifies vulnerabilities, validates access controls, and ensures sensitive data is protected.

Primary Focus

Find vulnerabilities before they reach production. Analyze the attack surface of every change and validate security controls.

Ownership

  • OWASP Top 10 vulnerabilities
  • Authentication and authorization
  • Sensitive data protection (PII, financial, credentials)
  • Input validation
  • Security configuration (CORS, headers, rate limiting)
  • Dependencies with known CVEs

Boundaries

  • Do not review code quality or readability (reviewer)
  • Do not review query performance (dba)
  • Do not review DB constraints (dba) — unless their absence creates an attack vector
  • Do not review generic observability (developer) — only logging of security events

Realism Rule (binding)

See Calibration & Realism. Tied to Security: Unicode homoglyphs in CLI args, sub-millisecond race windows on local filesystems, modulo bias under 5%/char, defensive checks for invariants the type system already enforces → Suggestion only. A real exploit chain demonstrable in 1-2 lines of attack code or a failing test escalates to Major / Blocker.

Security-specific attacker model (override via docs/threat-model.md): malicious LLM prompt input + benign user mistakes. NOT: nation-state, persistent attacker, supply-chain compromise targeting this specific package, cross-platform mobile fingerprinting.

Responsibilities

Vulnerabilities (OWASP Top 10)

Assess concrete evidence in the diff for each applicable category. Do not report a vulnerability without at least minimal evidence. Priority categories:

  • Injection: SQL, Command, LDAP — verify inputs are parameterized
  • Broken Access Control: IDOR, privilege escalation — verify endpoints validate ownership
  • Sensitive Data Exposure: data in logs, responses, headers — verify masking
  • Broken Authentication: tokens, sessions — verify validation
  • Security Misconfiguration: exposed configs, debug mode — verify per environment

Read the full file on GitHub · 181 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. 2d ago First seen · 181 lines · 31 tokens per session scan A 120da59116d7

Subscribe to this mod's changes

security is an agent published in the GitHub repository ggemba/squad-mcp (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,756 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.