Skip to main content
Glama
1tylermitchell

Sairen

by 1tylermitchell
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
JavaScript
Remote

scan_canary_tokens

Scan HTML payloads for canary traps, honeypots, and tracking beacons. Detects hidden DOM traps and returns a structured risk score to block prompt injection.

Instructions

    [Cost: $0.0020 USDC on Base & Solana] Sub-2ms honeypot & canary trap scanner for HTML payloads.
    
    Keywords: canary detector, leak probe, token canary, honeypot scanner, prompt injection.
    Detects: invisible DOM honeypots, DNS canary tokens (canarytokens.org / interactsh),
    zero-width Unicode steganography, CSS url() tracking beacons, pixel-sized iframes/images,
    obfuscated trap links, meta-refresh redirects, form honeypot fields, noscript beacons.

    Returns structured threat report with risk_score (0–100), threat_level
    (clean/low/medium/high/critical), and per-finding positions.

    Args:
        html: Raw HTML content to scan.
        url: Optional source URL for context enrichment.
        checks: List of check names to enable (default: all).
                Values: dns_canary, zero_width, hidden_elements, css_beacons,
                pixel_trackers, trap_links, meta_refresh, form_honeypots,
                noscript_beacons, aria_hidden
        max_findings_per_type: Max findings per category, 1-50 (default: 10).
        payment_signature: x402 Base USDC transaction hash (defaults to dev mock key).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNo
htmlYes
checksNo
payment_signatureNo
max_findings_per_typeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.3.1

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It discloses the cost ($0.0020 USDC on Base & Solana), sub-2ms latency, x402 payment signature requirement, and the structure of the return value, which are all valuable. It does not cover failure modes, rate limits, or error behavior, so it is strong but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with cost and speed, then structured into keywords, detections, return shape, and arguments. It is generally efficient, though the keyword line and the long detection list are somewhat redundant for an agent that does not need search-oriented metadata.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations, so the description must explain both behavior and return values; it does so by naming risk_score, threat_level, and per-finding positions. Combined with the detection categories, cost, payment, and parameter docs, an agent has enough context to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry all parameter meaning. It does so thoroughly: it defines html as raw HTML, url as optional source context, checks with allowed values and default-all behavior, max_findings_per_type with a 1-50 range and default of 10, and payment_signature as an x402 Base USDC transaction hash with a dev mock default.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: a honeypot and canary trap scanner for HTML payloads. It also enumerates the specific threat classes it detects, which makes the tool's scope clear. However, it does not explicitly differentiate itself from the sibling tool scan_payload_safety or other security-related siblings, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit when-to-use, when-not-to-use, or alternative-tool guidance. It implies the tool is for scanning HTML payloads for canary and honeypot traps, but an agent receives no routing instructions relative to siblings such as scan_payload_safety or extract_web_markdown.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools