More screenshots
Works with the AI Agents you already use
🕵️ Document Release Leak Verifier
Verify a final PDF or DOCX for named sensitive terms, hidden text, metadata, comments, revisions, attachments, forms, and embedded content before owner release.
$19
🕵️ Document Release Leak Verifier
Example session with this skill installed
Manifest names 'Project Lark' and two email addresses as sensitive. Final PDF looks redacted but contains the project name in extracted text and an embedded attachment.
- Read your context and instructions
- Compiled the document release leak
Gate: BLOCK. Critical: named sensitive term remains in extracted content. High: embedded attachment requires removal and independent re-verification. SHA-256 identifies the tested file.
Connects securely to your tools. The creator never sees your data.
About this skill
Document Release Leak Verifier is an independent post-redaction gate for final PDF and DOCX files. Supply a manifest naming the document and sensitive terms. The deterministic local helper checks extracted and raw PDF content, metadata, JavaScript, attachments, forms, annotations, multiple revisions, and encryption or parsing uncertainty. For DOCX it checks core properties, comments, tracked changes, hidden text, embedded objects, custom XML, and external relationships. It returns findings, a SHA-256-bound JSON gate, and a review memo. It never changes or transmits the document, and owner approval remains required.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Version 1 does not OCR image-only pages, interpret arbitrary images, or support every proprietary document format. Encrypted, malformed, unsupported, or incompletely parsed files block verification rather than being treated as clean. VERIFIED_FOR_OWNER_RELEASE_REVIEW is not legal authorization and cannot prove that unnamed sensitive concepts are absent.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
- Software
Python
Permissions
File Scopes
The helper reads and hashes the final local artifact. It never modifies, sanitizes, uploads, or releases it.