> For the complete documentation index, see [llms.txt](https://burp-ai-agent.six2dez.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://burp-ai-agent.six2dez.com/user-guide/bountyprompt-actions.md). # BountyPrompt Actions BountyPrompt integration adds curated, tag-aware actions to the request/response context menu. It is optional and configured from the **Custom Prompts** settings tab. ## What This Adds * A dedicated **BountyPrompt** submenu in request/response context menus. * Curated prompt loading from a local JSON directory. * Selective context extraction using `[HTTP_*]` tags. * Optional automatic Burp issue creation for prompts with `outputType = issue`. ## Enable and Configure Open **Custom Prompts** in the bottom settings panel and configure the **BountyPrompt integration** section: * **Enabled** * **Prompt directory** * **Auto-create issues** * **Issue threshold** * **Enabled prompt IDs** Reference defaults are documented in [Settings Reference](/reference/settings-reference.md). ## Curated Prompt Set Only curated IDs are loaded by design. ### Detection * `API_Keys_Exposure_Detection` * `CSRF_Vulnerability_Assessment` * `Security_Headers_Analysis` * `Vulnerable_Software_Detection` * `Vulnerable_File_Upload_Endpoint_Detection` * `Sensitive_Error_Messages_Detection` ### Recon * `Extract_Endpoints` ### Advisory * `Web_Attack_Suggestions` ## Tag-Aware Context Resolution BountyPrompt JSON `userPrompt` values can include these tags: | Tag | Injected Data | | ---------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | `[HTTP_Requests]` | Redacted raw HTTP requests | | `[HTTP_Requests_Headers]` | Request headers only | | `[HTTP_Requests_Parameters]` | Parsed request parameters; cookie-typed values are `[STRIPPED]` and values with sensitive-looking parameter names are `[REDACTED]` in STRICT/BALANCED | | `[HTTP_Request_Body]` | Request body only | | `[HTTP_Responses]` | Redacted raw HTTP responses | | `[HTTP_Response_Headers]` | Response headers only | | `[HTTP_Response_Body]` | Response body only | | `[HTTP_Status_Code]` | Response status code | | `[HTTP_Cookies]` | Request/response cookie lines | Unknown `[HTTP_*]` tokens are removed at resolution time. ## Privacy and Determinism Behavior BountyPrompt actions follow the same privacy controls as other actions: * Each raw request/response tag value is passed through the active redaction policy while the tag is resolved. * STRICT/BALANCED/OFF policies apply to the selected fields. * Host pseudonyms are stable for the same anonymization salt. The resolver preserves the request/response order supplied by Burp; the determinism toggle is reported in the preview but does not reorder BountyPrompt selections. * Parameter rendering is carrier-aware, not value-complete. In `[HTTP_Requests_Parameters]`, a secret-shaped value in a URL/body parameter whose name does not look sensitive can remain unchanged even in `STRICT` or `BALANCED`. Review the action preview before sending; see [Redaction Coverage](/privacy-and-logging/limitations.md#redaction-coverage-and-known-boundaries). ## Prompt Composition Each action composes two parts: 1. **System Instructions** from the BountyPrompt JSON `systemPrompt`. 2. **User Task** from resolved `userPrompt` after tag substitution. The resulting action text is shown in the standard context preview and, after confirmation, sent as a chat action through the selected backend. Backend framing and any separate system-role profile are added after that preview. ## Issue Creation Rules Issue creation is attempted only when all conditions are true: 1. Prompt `outputType` is `issue`. 2. **Auto-create issues** is enabled. 3. Parser extracts one or more findings. 4. Parsed confidence is greater than or equal to **Issue threshold**. Additional behavior: * Findings containing `NONE` are treated as no finding. * JSON outputs are parsed from direct JSON or fenced JSON blocks. * If valid JSON findings are not extracted, fallback parsing treats up to 12,000 characters of raw model output as one finding using the prompt definition's severity and confidence. That fallback can cross the issue threshold, so every auto-created issue still requires manual validation. * Issue names are prefixed as `[AI][BountyPrompt] ...`. * Duplicate issues (same base URL and same issue name) are skipped. ## Menu and UI Behavior * Menu appears as **BountyPrompt** under request/response actions. * Entries are grouped in **Detection**, **Recon**, and **Advisory**. * Entry labels are the prompt titles; the submenu itself does not include the selected-item count. * If disabled or unresolved, submenu is shown disabled with tooltip guidance. ## Operational Limits * Only curated IDs are loaded. * Only IDs listed in **Enabled prompt IDs** are allowed. * Definitions are parsed into an off-EDT cache at startup and after settings are saved. While the first cache load is pending, the submenu is disabled with a loading tooltip. * Per-tag context is truncated before model submission: * **Detection**: `2500` chars per chunk, `10000` chars per tag. * **Recon**: `3500` chars per chunk, `14000` chars per tag. * **Advisory**: `3000` chars per chunk, `12000` chars per tag. * Up to 20 selected request/response items are attached to created issues. ## Troubleshooting For menu visibility, loading errors, and issue creation diagnostics, see [Troubleshooting](/reference/troubleshooting.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://burp-ai-agent.six2dez.com/user-guide/bountyprompt-actions.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.