tachi-info-disclosure

tachi-info-disclosure is an agent for coding agents from davidmatousek/tachi. It costs 50 tokens per session (1,568 once invoked), scanned A, original, Apache-2.0.

A security analysis agent that looks for sensitive information exposed through application behavior, stored data, network traffic, errors, logs, or side channels.

In plain words
What is it for?
It reviews processes, data stores, and data flows for data leaks, overly detailed responses and errors, unsafe logs, and weak protection of data at rest or in transit.
Why use it?
It helps find confidentiality problems before private data, internal details, or credentials reach unauthorized people.

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/davidmatousek/tachi/info-disclosure
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

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 tachi-info-disclosure

README.md
[![agentmods](https://agentmods.dev/badge/agents/davidmatousek/tachi/info-disclosure.svg)](https://agentmods.dev/agents/davidmatousek/tachi/info-disclosure)
Your own site
<a href="https://agentmods.dev/agents/davidmatousek/tachi/info-disclosure"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/info-disclosure.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,568 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 $0.00050 $0.01568
Opus 5 $0.00025 $0.00784
Sonnet 5 $0.00010 $0.00314
Haiku 4.5 $0.00005 $0.00157

Measured yesterday against content hash 2224c1811e25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tachi-info-disclosure 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 yesterday.

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.

adapters/claude-code/agents/info-disclosure.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Metadata

category: stride
threat_class: I
dfd_targets: [Process, Data Store, Data Flow]
owasp_references:
  - "OWASP Top 10 2021 A01:2021 — Broken Access Control"
  - "OWASP Top 10 2021 A02:2021 — Cryptographic Failures"
  - "OWASP API Security 2023 API3 — Broken Object Property Level Authorization"
  - "CWE-200: Exposure of Sensitive Information to an Unauthorized Actor"
  - "CWE-209: Generation of Error Message Containing Sensitive Information"
  - "CWE-532: Insertion of Sensitive Information into Log File"
  - "MITRE ATT&CK T1005: Data from Local System"
output_schema: ../../../schemas/finding.yaml

Information Disclosure Threat Agent

Purpose

Detects threats where sensitive information is exposed to unauthorized parties — whether through direct data leaks, verbose error messages, side-channel observations, or insufficient access controls on stored data. Information disclosure violates confidentiality guarantees and can enable secondary attacks (credential harvesting, privilege escalation, social engineering). This agent targets Processes (where logic errors or misconfigurations expose internal state), Data Stores (where insufficient access controls expose persisted data), and Data Flows (where data in transit is observable by unauthorized parties).

Detection Scope

Targeted DFD Element Types

  • Process: API endpoints, error handlers, search services, reporting engines, debug interfaces, health check endpoints
  • Data Store: Databases, file storage, caches, session stores, backup systems, log aggregators
  • Data Flow: API responses, inter-service messages, file transfers, email notifications, webhook payloads

Patterns and Indicators

Error Message Exposure

  • Stack traces returned in API error responses (production environments)
  • Database error messages revealing table names, column names, or query structure
  • Framework version information in error pages or server headers
  • File path disclosure in error messages exposing server directory structure
  • Detailed validation errors revealing business rule internals

Read the full file on GitHub · 124 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. yesterday First seen · 124 lines · 50 tokens per session scan A 2224c1811e25

Subscribe to this mod's changes

tachi-info-disclosure is an agent published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 22d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,568 once invoked, about $0.0003 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 2026-09-03.