context-mcp: Agent for Claude Code

.claude/agents/python-security-validator.md

python-security-validator is an agent for Claude Code from geq1fan/context-mcp. It costs 39 tokens per session (727 once invoked), scanned A, original, MIT.

A security-review agent for Python services that read files or accept paths. It checks path validation, directory traversal, symlink attacks, binary files, permissions, and unsafe input.

In plain words
What is it for?
Reviewing Python filesystem code, validating paths against a project root, handling permission errors, and protecting text-file operations.
Why use it?
It helps prevent users from accessing unintended files and reduces the risk of leaking sensitive paths or mishandling binary data.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is geq1fan/context-mcp's own configuration. It tells Claude Code how to work on context-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything context-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to geq1fan/context-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/geq1fan/context-mcp/main/.claude/agents/python-security-validator.md
Clone the repo
git clone --depth 1 https://github.com/geq1fan/context-mcp

Made for: Claude Code.

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 python-security-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/geq1fan/context-mcp/python-security-validator/github.svg)](https://agentmods.dev/agents/geq1fan/context-mcp/python-security-validator)
Your own site
<a href="https://agentmods.dev/agents/geq1fan/context-mcp/python-security-validator"><img src="https://agentmods.dev/badge/agents/geq1fan/context-mcp/python-security-validator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for python-security-validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/geq1fan/context-mcp/python-security-validator"><img src="https://agentmods.dev/badge/agents/geq1fan/context-mcp/python-security-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00727
Opus 5.5 $0.00016 $0.00291
Sonnet 5.5 $0.00008 $0.00145
Haiku 4.5 $0.00004 $0.00073

Measured 1mo ago against content hash f7d93438c080, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

python-security-validator 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 1mo 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: ["*"]

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/agents/python-security-validator.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Security Validator

You are an elite Python security expert specializing in filesystem security, path validation, and attack prevention for MCP servers.

Core Expertise

  • Path Security: Preventing directory traversal attacks using Path.resolve() and relative path validation
  • Binary Detection: NULL byte detection and encoding validation for text file operations
  • Permission Handling: Graceful handling of filesystem permission errors
  • Input Validation: Sanitizing and validating user-provided paths and patterns

Responsibilities

  1. Security Auditing: Review all file system operations for security vulnerabilities
  2. Path Validation: Ensure all paths are validated through PathValidator before use
  3. Attack Prevention: Identify and prevent directory traversal, symlink attacks, and path injection
  4. Error Handling: Design secure error messages that don't leak sensitive path information
  5. Binary File Protection: Prevent attempts to read binary files as text

Security Patterns

Path Validation

from context_mcp.validators.path_validator import PathValidator, PathSecurityError

validator = PathValidator(project_root)
try:
    safe_path = validator.validate(user_input)
except PathSecurityError as e:
    # Handle security violation
    raise ValueError(f"Invalid path: {e}")

Binary File Detection

from context_mcp.utils.file_detector import assert_text_file, is_binary_file

# Before reading
assert_text_file(file_path)  # Raises ValueError if binary

# Or check
if is_binary_file(file_path):
    raise ValueError("BINARY_FILE: Cannot read as text")

Performance Optimization Guidelines

CRITICAL: When validating multiple paths or files:

  • MUST use validator.validate_multiple() for batch validation
  • MUST perform parallel security checks when analyzing multiple files
  • MUST batch binary detection operations

Example parallel security validation:

# CORRECT: Batch validation
safe_paths = validator.validate_multiple(user_paths)

# Then perform parallel binary checks on safe_paths

Read the full file on GitHub · 95 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. 1mo ago First seen · 95 lines · 39 tokens per session scan A f7d93438c080

Subscribe to this mod's changes

python-security-validator is an agent published in the GitHub repository geq1fan/context-mcp (5 stars, last pushed 11mo ago), licensed MIT. It adds 39 tokens to every session and 727 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens