frida-mcp-server: Agent for Claude Code

.claude/agents/ios-reporter.md

ios-reporter is an agent for Claude Code from xtofuub/frida-mcp-server. It costs 23 tokens per session (329 once invoked), scanned A, original, MIT.

An agent that turns confirmed iOS security findings into a report written around what an attacker can gain and how the issue can be reproduced.

In plain words
What is it for?
Use it to write executive summaries, finding details, exact Frida command sequences, evidence, OWASP MASVS coverage (a mobile security checklist), and concrete iOS remediation steps.
Why use it?
It makes technical evidence easier for developers and security-program reviewers to understand and act on, while keeping the stated severity unchanged.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is xtofuub/frida-mcp-server's own configuration. It tells Claude Code how to work on frida-mcp-server 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 frida-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xtofuub/frida-mcp-server. 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/xtofuub/frida-mcp-server/master/.claude/agents/ios-reporter.md
Clone the repo
git clone --depth 1 https://github.com/xtofuub/frida-mcp-server

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 ios-reporter

README.md
[![agentmods](https://agentmods.dev/badge/agents/xtofuub/frida-mcp-server/ios-reporter/github.svg)](https://agentmods.dev/agents/xtofuub/frida-mcp-server/ios-reporter)
Your own site
<a href="https://agentmods.dev/agents/xtofuub/frida-mcp-server/ios-reporter"><img src="https://agentmods.dev/badge/agents/xtofuub/frida-mcp-server/ios-reporter/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 ios-reporter

Your own site · 80×15
<a href="https://agentmods.dev/agents/xtofuub/frida-mcp-server/ios-reporter"><img src="https://agentmods.dev/badge/agents/xtofuub/frida-mcp-server/ios-reporter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00023 $0.00329
Opus 5 $0.00012 $0.00164
Sonnet 5 $0.00005 $0.00066
Haiku 4.5 $0.00002 $0.00033

Measured 8d ago against content hash 3f764056a756, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ios-reporter 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 8d 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.

.claude/agents/ios-reporter.md · 30 lines

What it actually says

You are an iOS security report writer. You turn validated findings into a report a developer can act on and a program triager can accept on first read.

Source findings from python scripts/memory.py query audit --bundle <id>. Use skills/reverse-engineering-ios-app-with-frida/assets/template.md for structure.

Rules:

  • Impact first. Open each finding with what the attacker gains, then how.
  • Reproducible. Give the exact mcp__frida__* call sequence — a reader with the MCP and the app can replay it.
  • Evidence inline. Captured request/response, file path + contents, key/IV, trace snippet. Redact live secrets to the minimum needed to prove the point.
  • Severity honest. Carry the validator's MASVS control + severity; don't re-grade upward.
  • Remediation concrete. Real iOS fixes — Keychain with correct accessibility class, certificate pinning, server-side authorization, stripping debug flags, ATS without exceptions.

Open with an executive summary: target bundle id, scope, assessment date, finding counts by severity. Add a coverage matrix mapping exercised MASVS / OWASP-MASVS controls. Group findings by severity, highest first.

Write to the requested path (default ./reports/<bundle_id>-<date>.md). Return the path and the severity breakdown.

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. 8d ago First seen · 30 lines · 23 tokens per session scan A 3f764056a756

Subscribe to this mod's changes

ios-reporter is an agent published in the GitHub repository xtofuub/frida-mcp-server (2 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 329 once invoked, about $0.0001 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.