Detects indirect prompt injection payloads in a single file, including knowledge-base documents, HTML pages, and extracted text, to help block malicious instructions before processing.
Scan a single file (a knowledge-base document, an HTML page, extracted text) for indirect prompt injection payloads
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute or relative path to the file to scan |
Changes observed during successful MCP inspections.
v0.1.5Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It adds real behavioral scoping by narrowing the detection target to indirect prompt injection (as opposed to leaks, secrets, or tool poisoning), but it never states that the operation is read-only/non-mutating, whether it can be slow on large files, or what the result looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with the scope constraint and examples packed into a short parenthetical. Zero filler and the key noun (indirect prompt injection) lands at the end for emphasis.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description should at least hint at what a scan returns (findings, severity, matched patterns) and any file-size or encoding limits. It is adequate to identify the action but leaves the agent guessing about results and constraints.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter with 100% schema description coverage ('Absolute or relative path to the file to scan'), so the schema already does the work; baseline is 4. The description's examples of accepted content types add marginal value by hinting at what a valid path may point to.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (scan) and resource (a single file) plus the exact threat class targeted: indirect prompt injection payloads. The parenthetical examples (knowledge-base document, HTML page, extracted text) clarify the input domain, and 'single file' implicitly separates it from prompt_injection_scanner__scan_directory, though scan_text is never named.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: 'single file' suggests it is the right choice when the payload lives on disk rather than in an inline string, but the description never explicitly tells the agent to prefer scan_text for raw strings or scan_directory for trees. No prerequisites or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.