client delivery preflight auditor

    1

    Automated read-only preflight auditor for client deliveries to catch PII leaks, placeholders, and packaging errors.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    client delivery preflight auditor

    Example session with this skill installed

    Run a preflight audit on the project_alpha_handover.zip file in the current directory. Check for any blockers before I send this to the client.

    • Read your context and instructions
    • Compiled the client delivery preflight
    • Generated the document

    I have completed the preflight audit for project_alpha_handover.zip. The archive was extracted to a temporary directory for analysis and has been purged following the audit.

    Preflight Audit Report

    Target: project_alpha_handover.zip
    Audited At: 2023-10-27 14:22:01 UTC
    State: HOLD

    ⚠️ Critical Findings (causes HOLD)

    • Sensitive Data Detected: Found potential credentials in config/settings.yaml.
    • Stale Placeholders: File docs/User_Guide.md contains 3 instances of {{TBD}} in the "Setup" section.

    Evidence Gap: The report Alpha_Performance_Summary.pdf claims "99.9% uptime achieved," but no corresponding log files or monitoring data were found in the evidence/ folder.

    • Missing Deliverable: System_Architecture_Diagram.pdf referenced in the README is not present in the archive.

    ⚠️ Warnings (recommended to review)

    • Packaging Mistake: Found .DS_Store and __MACOSX files which should be stripped before final release.
    • Suspicious File Type: scripts/setup_linux.sh is an executable script; ensure this is intended for the client.
    • Duplicate File: Logo_Final.png exists in both root and /assets subfolder.

    ℹ️ Information / Summary

    • Total Files: 24
    • Total Size: 4.2 MB
    • Key Deliverables: README.md, Alpha_Performance_Summary.pdf, source_code.zip.

    🔒 Redacted Sensitive Values Detected

    • 1 x API Key pattern in config/settings.yaml [REDACTED: API_KEY]
    • 2 x Internal Email address in docs/Internal_Notes.txt [REDACTED: EMAIL]

    Recommendations

    1. Remove the plaintext API key from the config file and use environment variables or a placeholder.
    2. Complete the TBD sections in the User Guide.
    3. Include the monitoring logs in the evidence/ folder to support performance claims.
    4. Clean hidden system files using dot_clean or similar utility before re-zipping.

    Next steps

    • Address the critical sensitive data and placeholder findings.
    • Verify if the missing architecture diagram was intended for this release.
    • Re-run the preflight audit once the package is updated.

    project_alpha_handover.zip

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Manual delivery checks are error-prone and risk exposing sensitive data. Sending a ZIP with "TODO" placeholders, internal API keys, or missing evidence files damages client trust and compromises security.

    What it does

    • Scans folder structures and ZIP archives for packaging errors like hidden .git files or nested archives.
    • Identifies unedited placeholders, "lorem ipsum" text, and template leftovers in documents.
    • Detects potential PII and credentials, reporting them in a redacted format to maintain privacy.
    • Cross-references verbal claims like "guaranteed results" against the presence of supporting evidence files.
    • Issues a clear HOLD or READY status based on the severity of findings.

    Why this beats prompting it yourself

    A standard LLM prompt often hallucinates file contents or fails to maintain strict read-only boundaries. This skill enforces a structured preflight protocol that includes automated redaction of sensitive matches and objective evidence-gap analysis that goes beyond simple text scanning.

    Use cases

    • Auditing final project handovers for sensitive internal codenames or credentials.
    • Verifying marketing collateral for unsupported claims and broken appendix references.
    • Checking software delivery ZIPs for hidden system files and build artifacts.
    • Ensuring all required contract deliverables are present before client submission.

    Known limitations

    Cannot scan password-protected ZIPs. Content extraction for binary formats like PDF or DOCX depends on the presence of local textual extraction tools.

    Cannot audit password-protected or corrupted archives. Text extraction from binary files (PDF/DOCX) requires compatible environment tools. Does not perform repairs or deletions.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    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 2 months ago

    Permissions

    No special permissions declared or detected

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    The auditor scans ZIP archives and folder structures for 'TODO' placeholders, 'Lorem Ipsum' text, hidden system files like .git directories, and sensitive PII or internal credentials that could compromise a delivery.

    This skill is designed for use with AI agents capable of file system access and text processing; it works best when the agent has local extraction tools available for binary formats like PDF or DOCX.

    To protect your security, the skill operates in a structured read-only mode and reports potential PII or credentials in a redacted format, ensuring sensitive data isn't exposed during the audit process.

    You receive the complete skill definition, including the specialized preflight protocol and structured reporting logic, which can be integrated into your existing delivery workflow immediately.

    The skill performs a gap analysis by cross-referencing your document text against the provided file list, ensuring that if you mention a 'Case Study' or 'Appendix,' the corresponding file is actually present in the package.

    The skill cannot access password-protected archives, and while it excels at text-based files, its ability to scan binary documents depends on your agent's local text-extraction capabilities.

    New in Business & Operations