privacy-auditor

privacy-auditor is a skill for Claude Code from reatlat/fullstory-claude-plugin. It costs 52 tokens per session (1,254 once invoked), scanned A, original, MIT.

A privacy-checking tool for Fullstory, a service that records how people use websites and apps. It checks whether sensitive information, known as personally identifiable information (PII), is being captured in those recordings.

In plain words
What is it for?
Use it to review masking, blocking, page exclusions, and network exclusions, and to look for sessions where sensitive data may be visible.
Why use it?
It helps find broken or missing rules that could expose emails, form data, images, admin pages, or network requests in user-session recordings.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fullstory-claude-plugin plugin — 46 skills, 3 agents, 1 MCP server shipped together

Good fit Use it to review masking, blocking, page exclusions, and network exclusions, and to look for sessions where sensitive data may be visible.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/reatlat/fullstory-claude-plugin/privacy-auditor
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.

Any agent
npx skills add reatlat/fullstory-claude-plugin --skill privacy-auditor
Clone the repo
git clone --depth 1 https://github.com/reatlat/fullstory-claude-plugin

Made for: Claude Code.

Or install fullstory-claude-plugin, the plugin that ships this one along with the rest of its 46 skills, 3 agents, 1 MCP server.

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 privacy-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/privacy-auditor/github.svg)](https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/privacy-auditor)
Your own site
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/privacy-auditor"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/privacy-auditor/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 privacy-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/privacy-auditor"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/privacy-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,254 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00052 $0.01254
Opus 5 $0.00026 $0.00627
Sonnet 5 $0.00010 $0.00251
Haiku 4.5 $0.00005 $0.00125

Measured 11d ago against content hash 9200d6c055a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

privacy-auditor 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 11d 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.

skills/privacy-auditor/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Privacy Auditor

Audit your Fullstory session capture for PII exposure, verify privacy rules are working, and find sessions that may contain sensitive user data.

When to Use

  • "Are we accidentally capturing PII in sessions?"
  • "Check if our privacy masking rules are working"
  • "Did the recent deploy break any privacy exclusions?"
  • "Find sessions where user emails might be visible"
  • "Verify that the /admin pages are excluded from recording"
  • "Audit our recording block rules — are the right elements masked?"

Mental Model

Fullstory records everything users see and do. Privacy controls prevent sensitive data from being captured:

  1. Exclusion rules: Pages or elements excluded entirely from recording
  2. Masking rules: Elements that are recorded but with text/images replaced
  3. Block rules: Elements blocked from capture (not recorded at all)
  4. Network exclusions: API calls excluded from network capture

This skill verifies that these controls are working correctly.

Workflow

Step 1: Check current privacy configuration

Call fullstory:get_recording_block_rules to see what's currently configured:

  • Element selectors being masked or blocked
  • URL patterns being excluded from recording
  • Network URL patterns excluded from capture

Present the current rules to the user: "Here's what's currently configured. 12 element selectors masked, 3 URL patterns excluded, 1 network exclusion."

Step 2: Verify rules on actual sessions

Pull recent sessions and check if the rules are working:

fullstory:get_sessions(time_range="last_24_hours", limit=5)

For each session, use session_view to check pages that should have masked elements:

  • Navigate to a page with known sensitive elements (e.g., /checkout, /settings)
  • Check that password fields, credit card inputs, and other sensitive fields are masked
  • Verify that excluded pages (e.g., /admin) don't appear in session data at all

Step 3: Hunt for PII leaks

Look for common PII exposure patterns:

Read the full file on GitHub · 130 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. 11d ago First seen · 130 lines · 52 tokens per session scan A 9200d6c055a1

Subscribe to this mod's changes

privacy-auditor is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 29d ago), licensed MIT. It adds 52 tokens to every session and 1,254 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 2026-08-30.