More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Content Guard — Prompt Injection & Hidden-Char Scanner

    1

    - **Deterministic verdicts**: malicious / suspicious / clean / inconclusive with traceable PITAX rule IDs (e.g.

    Free

    1 useSecurity scanned
    AI Content Guard — Prompt Injection & Hidden-Char Scanner

    AI Content Guard — Prompt Injection & Hidden-Char Scanner

    Example session with this skill installed

    Is this email safe to summarize? inbox/partner-email.txt

    • Read your context and instructions
    • Compiled the ai content guard

    Verdict: malicious

    Scanned partner-email.txt (1 file, 196 bytes) with the local engine — no network, nothing executed.

    RuleTypeSeverity
    PIT-N-06Instruction override (document injection)high

    Evidence (redacted): rule PIT-N-06, length 40, sha 3f1c...9a2e, edges "请忽...示看" — full text never reproduced.

    What this means

    The email contains text that instructs an AI reading it to ignore existing instructions and print its system prompt — a classic indirect prompt-injection payload aimed at AI-assisted email workflows.

    Recommended handling

    • Do not forward the original text to any AI assistant; share only this redacted report.
    • Treat the sender as untrusted and verify via a second channel.
    • If you need a summary, summarize only the non-payload parts; the agent will refuse to quote the payload.

    Report artifacts

    JSON, SARIF 2.1.0 and a redacted Markdown summary are available for CI or ticketing workflows.

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

    About this skill

    What it does

    AI Content Guard is a defensive security skill for AI coding agents. When your agent is about to read, summarize, translate, or execute content from an untrusted source — received emails, downloaded documents, someone else's repo, unvetted AI config files — this skill scans it first with a local deterministic engine.

    • Deterministic verdicts: malicious / suspicious / clean / inconclusive with traceable PITAX rule IDs (e.g. PIT-N-06 prompt-injection, PIT-E-23 invisible characters, PIT-E-07 encoded payloads). The engine decides; the model only explains.
    • Zero-raw-text output contract: findings are reported redacted (rule ID + type + length + SHA-256 + 4-char edges). Attacker text never re-enters your agent's context through the report.
    • Filesystem guardrails: refuses system directories, browser profiles, password stores, SSH keys; sensitive files (.env, *.pem, id_rsa...) are name-only reported and never read; symlinks/reparse points not followed; bounded scans (files/bytes/depth/timeout).
    • 100% local: no network calls in the engine, no telemetry, no account.

    How it runs

    The ZIP ships SKILL.md plus Python scripts (scripts/entry.py + scripts/engine/). The agent materializes the scripts locally and runs:

    python entry.py --file <path>
    python entry.py --dir <repo>
    python entry.py --text "<pasted content>"
    

    Requires Python 3.10+. Works on macOS, Linux and Windows.

    Note for reviewers

    This is a defensive tool: its bundled detection corpus (references/rules.md, engine rule tables) intentionally contains attack-pattern strings because those strings are the detection signatures. Automated scanners may flag them — they are corpus, not capability.

    Requires Python 3 environment. Cannot scan system-protected directories or encrypted files. Large datasets may trigger timeout or depth limits. Local scan only, no network-based URL fetching.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    • Free with an Agensi account

    Requires

    Python 3.10+
    Local filesystem access (only the paths you pass)

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables

    The bundled engine reads only files the user explicitly passes (--file/--dir). System directories, password stores and SSH keys are refused; sensitive files are name-only reported and never read; symlinks/reparse points are not followed. The engine makes no network calls and never executes scanned content.

    Listed5 days ago
    Updated3 days ago

    What's inside

    Frequently Asked Questions

    Unlike LLMs, which can be tricked by the very injections they are trying to detect, this skill uses a deterministic Python engine that treats input as raw data. This prevents the scanner itself from being hijacked during the analysis process.

    The engine detects direct and indirect prompt injections, invisible Unicode characters used for 'jailbreaking,' and encoded payloads such as Base64 or Hex. It also audits AI-specific configuration files like .cursor/rules for malicious backdoors.

    This is a local, self-contained Python-based skill compatible with any environment that supports Python 3. It works alongside your existing agent workflows on Windows, macOS, or Linux without requiring external API calls.

    You receive the complete deterministic scanning engine, the 'entry.py' execution script, and documentation on how to integrate the JSON output into your agent's decision-making pipeline.

    To ensure performance and safety, the tool includes depth limits for directory scanning and timeouts for very large files. It focuses on scanning data and project files rather than system-level directories or sensitive personal keys.

    New in LLM Ops