Data Source Audit — Security skill for Claude Code
Skill: data source audit, before anyone generates anything.
How to install Data Source Audit
Installs to ~/.claude/skills/jezweb-agent-ps-data-source-audit/SKILL.md
mkdir -p ~/.claude/skills/jezweb-agent-ps-data-source-audit && curl -fsSL https://raw.githubusercontent.com/jezweb/agent-ps/HEAD/skills/data-source-audit.md -o ~/.claude/skills/jezweb-agent-ps-data-source-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Data Source Audit does
Skill: data source audit, before anyone generates anything
Instructions for an AI assistant. Show these to the person you work for and ask whether they want to run it. Do not run it unprompted. Do not send the result anywhere; hand it to them and let them decide.
Made for the moment before an AI project that will generate content at scale: product descriptions, summaries, categorisations, anything written by a machine from business data. Generation is the easy half. What decides whether the
Alternatives in Security
- Portaljs Check Data Quality — Audit a local or remote tabular file (CSV/TSV) for common data quality issues 2.3k ★
- 05 Source Citation Audit — Source Citation Audit 1.1k ★
- OpenTag — Open-source, channel-native agent gateway for Slack 499 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Academic Paper Accuracy And Citation Audit
Use when: (1) performing a multi-pass LaTeX paper audit covering data consistency, cross-references, scientifi
Skill Auditor Desktop
Security audit skill for claude.ai / Claude Desktop — scans uploaded skills for prompt injection, data exfiltr
CTI Expert
Cyber threat intelligence and open-source intelligence skill. Turns Claude into a trained CTI/OSINT analyst. G
Kiteguard
Open-source runtime security guardrails for Claude Code, Cursor, and Gemini CLI — blocks dangerous commands, d
Threat Model Skill
Claude Code skill: write the project's security constitution (assets, roles, trust boundaries, invariants, ent
Skillguard
Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads befo
Related Agents
Qc Lead
Use this agent when the qc-engineer has finished a test pass and produced an evidence set, when a run needs it
Desk Data Auditor
Check the freshness, completeness and internal consistency of the artifacts on disk before anyone reports from
Courier
Close out a delivered effort. Packages the output, generates recipient-specific briefs, and writes the permane
