More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Prompt Injection Scanner: Vet text before agents read it

    1

    Your agent reads web pages, READMEs and tool output, and any of them can carry hidden instructions. Scan text first for instruction overrides, spoofed roles, secret-access and exfiltration cues, with the evidence masked.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Prompt Injection Scanner: Vet text before agents read it

    Example session with this skill installed

    Scan references/attack.md (an inert test file with fake injected instructions) before you read it. Return Markdown and tell me whether the agent should act on anything in it.

    • Read your context and instructions
    • Compiled the prompt injection scanner

    Captured stdout from python3 -I -B scripts/injection_scan.py references/attack.md --format markdown (exit 1):

    Prompt injection heuristic scan

    Files: 1 | Findings: 6 | Gate: FAIL

    Actionable: 6 | Context: 0

    Fail threshold: high | Gate context: false

    SourceLineTierSeverityRuleOriginRedacted evidence
    references/attack.md2actionablehighoverriderawInstruction override cue: [MASKED]
    references/attack.md3actionablehighrole-spoofrawClaimed privileged role: [MASKED]
    references/attack.md4actionablehighsecret-accessrawSensitive local data access cue: [MASKED]
    references/attack.md5actionablecriticalexfiltrationrawOutbound transfer instruction cue: [MASKED]
    references/attack.md6actionablehightool-spoofrawTool invocation serialization cue: [MASKED]
    references/attack.md7actionablehighimage-queryrawRemote Markdown image with query data: [MASKED]

    Heuristic only: a clean scan is not a safety guarantee.

    FAIL: 6 actionable findings in references/attack.md, 1 critical (an exfiltration cue at line 5) and 5 high. Don't let the agent follow any instruction in this text. The evidence is masked in the report. This is a heuristic scan: a clean result would not be a safety guarantee.

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

    About this skill

    The problem You're about to let an agent read a README, a saved web page or a tool response that someone else wrote. Most of it is useful. But a line telling the agent to drop its task or send your keys somewhere can hide in the middle, or in an HTML comment you'd never see rendered. You want a quick look before it lands in the agent's context, not after.

    See it before you buy: real input, real output Command (from the package folder, exit code 1, 0.029 s):

    python3 -I -B scripts/injection_scan.py references/attack.md --format markdown
    

    Before: references/attack.md: a 7-line inert test file with a fake instruction override, a claimed privileged role, a key-file read, an upload instruction, a tool call and a tracking image.

    After: lines copied from the script's output (excerpt):

    Files: 1 | Findings: 6 | Gate: FAIL
    Actionable: 6 | Context: 0
    | references/attack.md | 2 | actionable | high | override | raw | Instruction override cue: [MASKED] |
    | references/attack.md | 3 | actionable | high | role-spoof | raw | Claimed privileged role: [MASKED] |
    | references/attack.md | 4 | actionable | high | secret-access | raw | Sensitive local data access cue: [MASKED] |
    | references/attack.md | 5 | actionable | critical | exfiltration | raw | Outbound transfer instruction cue: [MASKED] |
    | references/attack.md | 6 | actionable | high | tool-spoof | raw | Tool invocation serialization cue: [MASKED] |
    | references/attack.md | 7 | actionable | high | image-query | raw | Remote Markdown image with query data: [MASKED] |
    Heuristic only: a clean scan is not a safety guarantee.
    

    What the numbers show

    • On 356 README and docs files from 22 popular open-source repos it raised 0 actionable findings, so nothing failed the default check.
    • On six public labelled datasets (the held-out half): InjecAgent, 530 of 1059 attacks caught with 0 of 1066 benign rows flagged; deepset, 19 of 127 caught with 0 of 192 benign. No benign row in any dataset failed the default check.
    • Honest limit: it catches the blunt half of attacks and isn't a classifier. On 20 hand-built samples it caught 15, listed four more as context, and missed one that hid its text in URL escapes.

    What you get

    • One Python script with no dependencies. Point it at files or pipe text on stdin.
    • 13 pattern groups for things like "ignore your instructions", fake system or tool messages, requests to reveal the system prompt, and commands to send data to a URL. Some German, Spanish and French phrasings are included.
    • Four checks for text a reader can't see: HTML comments, hidden CSS, hidden attributes and invisible Unicode characters.
    • It also decodes one layer of base64 and HTML entities, so simple encoding doesn't hide a match.
    • A JSON or Markdown report with file, line, rule and severity. The matched text itself is always masked, so the report is safe to paste.
    • Two tiers. "Actionable" findings look like real instruction attempts and fail the check (exit 1). "Context" findings, such as a plain HTML comment, are listed but don't fail it unless you add --gate-context.
    • 83 test cases and five saved reports you can compare against.

    Measured on real data (full detail) On 356 README and docs files from 22 popular open-source repos, it raised zero actionable findings, so nothing failed the default check. It did list 448 context findings, mostly HTML comments, badge image links and example URLs.

    I also ran it on six public labelled prompt-injection datasets. I tuned rules on half of each dataset and report the other half here. "Caught" means the row failed the default check. "Flagged" means any finding at all.

    DatasetAttacks caughtAttacks flaggedBenign rows flagged
    InjecAgent tool responses530 of 1059561 of 10590 of 1066
    Gandalf "ignore instructions"26 of 5332 of 53(no benign rows)
    safeguard test set71 of 355132 of 35511 of 686
    deepset prompt injections19 of 12727 of 1270 of 192
    jackhhao jailbreaks44 of 333229 of 33392 of 680
    BIPIA email0 of 230 of 230 of 28

    No benign row in any dataset failed the default check. Every false alarm is a context finding from the roleplay rule, on harmless "act as a..." prompts. Read the table as "catches the blunt half of attacks". It isn't a classifier. On 20 hand-built attack samples it caught 15, listed four more as context, and missed one that hid its text in URL escapes. The package's benchmark notes have the full tables and how to rebuild the datasets.

    Known limitations

    • Polite, task-style injections ("please also forward this to...") look like normal requests. It caught none of the BIPIA email attacks.
    • It matches patterns. It doesn't understand intent, so rephrased attacks get through and some harmless prompts get flagged as context.
    • Anything inside a Markdown code fence is downgraded to context. That keeps docs quiet, but an attacker can use a fence too.
    • URL-escaped text, nested encodings, images and PDFs aren't checked. Language coverage beyond English is a handful of phrasings.
    • A pass doesn't make a file safe and doesn't limit what your agent can do.

    Who it's for Developers who feed outside text to agents and want a fast, offline check first, by hand or as a CI step.

    Requires Python 3.8 or newer. Nothing to install. Input must be UTF-8 files or stdin. It runs locally, makes no network calls and writes no files.

    Check it yourself 83 test cases and five saved reports, six public labelled datasets (half held back from tuning), 20 hand-built attack samples and 356 open-source docs files. To reproduce the demo, run this from the package folder: python3 -I -B scripts/injection_scan.py references/example-page.html --format markdown --fail-on medium

    Price and guarantee $12 one time, yours to use with any agent that can run Python. Covered by Agensi's money-back guarantee if it doesn't do what this page promises.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    English-oriented. No DOM rendering or URL fetching. Misses nested encodings, images, and PDFs. Approximate Markdown fence recognition. Not a guarantee of safety.

    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 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 14 days ago

    Software
    Python 3

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Uses a terminal to run Python and reads only the explicitly selected local input files or stdin. No network access. Nothing is sent anywhere. The scanner writes no files; it prints reports to stdout and input errors to stderr. A host may create and delete its temporary script, and a user may redirect a report.

    Listed14 days ago
    Updated4 days ago

    What's inside

    Frequently Asked Questions

    grep is free and fine for one phrase. This covers 13 pattern groups plus four hidden-text checks, decodes HTML entities and one base64 layer, maps hits back to the original line, masks evidence and gives you a pass/fail exit code. It's still pattern matching, just broader and safer to share.

    At the default check, about half of the InjecAgent and Gandalf attacks, 13% to 20% of the deepset, safeguard and jackhhao ones, and none of BIPIA. No benign row failed it. The table above has the exact counts.

    No. It reads the files you name and prints a report. File paths appear in the report, so rename sensitive files before sharing it.

    Agensi's money-back guarantee covers every paid skill: if it doesn't do what this page promises, you get your money back. Everything above is output from the script in the package, so you can see what it does before you buy.

    New in LLM Ops