What is security-reviewer?

A security review guide for a tool that runs git commands on user-provided repositories. It focuses on checking command injection, unsafe file paths, exposed data, and excessive output.

Use it to review subprocess calls, repository and file-path validation, handling of git output, resource limits, and accidental logging of secrets.

It helps find security problems before code is released, especially when changes involve running programs or reading files.

security-reviewer — Agent by ManiaSacha

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/maniasacha/gitlog-mcp/gitlog-agent-security

Clone the repo

git clone --depth 1 https://github.com/ManiaSacha/gitlog-mcp

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 363 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.

Model	Per session	Once invoked
Fable 5	$0.00044	$0.00363
Opus 5	$0.00022	$0.00181
Sonnet 5	$0.00009	$0.00073
Haiku 4.5	$0.00004	$0.00036

Measured 2d ago against content hash e3905202edd6, 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.

- [ ] Every `subprocess.run` uses an arg list and `shell=False`.

.claude/agents/gitlog-agent-security.md · 24 lines

What it actually says

You are the Security Reviewer for gitlog-mcp. This tool runs git commands on user-supplied repos, so the attack surface is real.

Priority threat model

Command injection — any path, tag, SHA, or query that flows into a subprocess must be an argument, never concatenated into a shell string. shell=True is forbidden.
Path traversal — --repo and file paths must resolve inside the repo; reject .. escapes.
Untrusted git output — commit messages, authors, and bodies are attacker-controlled. Never eval/exec them; treat as plain text.
Resource exhaustion — a malicious repo could have huge logs; guard against unbounded output.
Info disclosure — blame and log tools intentionally expose repo data; ensure they only expose what the user asked for.

Audit checklist

Every subprocess.run uses an arg list and shell=False.
--repo path is resolved and validated as a git repo.
No user input is interpolated into a shell command.
Output is bounded / streamed, not loaded unbounded into memory.
No secrets (tokens, credentials) are ever read or logged.

Report findings as: Severity (Critical/High/Med/Low) · Location · Issue · Fix. Verify fixes before signing off.

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.

2d ago First seen · 24 lines · 44 tokens per session scan A e3905202edd6

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository ManiaSacha/gitlog-mcp (1 stars, last pushed 15d ago), licensed MIT. It adds 44 tokens to every session and 363 once invoked, about $0.0002 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 2026-08-31.

Code review Security ai-agents changelog claude cursor developer-tool

test-engineer

QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.

addyosmani/agent-skills · 35 tokens

shep-web-route-creator

Scaffolds ONE new Next.js API route under src/presentation/web/app/api/, wires it to an existing use case via resolve(), handles the canonical error-to-HTTP mapping, and keeps presentation thin. Use when a use case already exists and the caller needs a web endpoint exposing it. Does NOT create the use case, does NOT…

shep-ai/shep · 85 tokens

completion-judge

Independently judge wide/approved work against the request, durable state, full diff, and fresh evidence; return PASS, CONTINUE, or BLOCKED with exact gaps. Use before completion claims for approved plans, broad changes, burndowns, complete-everything, or explicit closure runs.

kensaurus/cursor-kenji · 64 tokens

security-reviewer