farhoodlabs/trebuchet
8
0
Fork 0
Code Issues Pull Requests 5 Actions Packages Projects Releases Wiki Activity

feat: use structured outputs for vuln agent exploitation queues (#267)

Browse Source 
* feat: add structured outputs for vuln agent exploitation queues

Use Claude Agent SDK's native outputFormat to get schema-validated JSON
queue data from vulnerability analysis agents instead of relying on
save-deliverable tool calls for queue files.

- Add Zod schemas for all 5 vuln types (injection, xss, auth, ssrf, authz)
- Thread outputFormat through SDK call chain (executor → message handlers)
- Write structured_output to disk as queue JSON before validation
- Handle error_max_structured_output_retries as retryable failure
- Update vuln prompts to use structured output for queues
- Keep save-deliverable for markdown deliverables (unchanged)

* fix: correct structured output schema conversion for Claude Agent SDK

Use draft-07 target for z.toJSONSchema() instead of the default
draft-2020-12, which the SDK's AJV validator doesn't support. Update
pipeline-testing prompts to use structured output instead of raw JSON
responses.

* refactor: remove save-deliverable references for queues in vuln prompts

Queues are now captured via structured outputs, so vuln agents no longer
need to use save-deliverable for queue JSON. Removes references to
"structured response/output" phrasing and aligns all prompts to use
consistent "exploitation queue" terminology.

* refactor: remove queue support from save-deliverable

Queues are now produced via structured outputs, so save-deliverable no
longer needs queue-related code. Removes queue enum values, filename
mappings, JSON validation, and updates all prompt tool descriptions to
match the simplified CLI interface.

* fix: instruct vuln agents to save deliverable before exploitation queue

The structured output tool terminates the agent session when called.
Agents were calling it before saving their deliverable markdown,
causing output validation failures and unnecessary retries.

* refactor: remove explicit exploitation queue output instructions from vuln prompts

The Claude Agent SDK automatically captures structured output on the
last turn when outputFormat is set. Prompts explicitly telling agents
to produce the queue caused them to call StructuredOutput mid-session,
conflicting with the SDK mechanism and silently dropping the output.

Removed exploitation_queue_requirements sections and queue references
from conclusion triggers. Added note that the queue is captured
automatically. Updated Your Output to point to the deliverable markdown.
This commit is contained in:
ezl-keygraph
2026-04-02 01:12:00 +05:30
committed by GitHub
parent 6a0c8ce710
commit 2a433f090f
28 changed files with 273 additions and 236 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/worker/prompts/exploit-authz.txt
+3 -3
View File
@@ -131,10 +131,10 @@ You are the **Privilege Escalation Specialist** - proving tangible impact of bro
<cli_tools>
- **Browser Automation (playwright-cli skill):** Essential for interacting with complex authorization flows, testing role-based access controls in browser contexts, and verifying privilege escalation through UI elements. Invoke the `playwright-cli` skill to learn available commands. Always pass `-s={{PLAYWRIGHT_SESSION}}` to every command for session isolation.
- **save-deliverable (CLI Tool):** Saves your deliverable files with automatic validation.
- **Usage:** `save-deliverable --type <TYPE> --file-path <path>` or `--content '<json>'`
- **Returns:** JSON to stdout: `{"status":"success","filepath":"...","validated":true}` or `{"status":"error","message":"...","retryable":true}`
- **Usage:** `save-deliverable --type <TYPE> --file-path <path>` or `--content '<text>'`
- **Returns:** JSON to stdout: `{"status":"success","filepath":"..."}` or `{"status":"error","message":"...","retryable":true}`
- **For large reports:** Write to disk first, then use `--file-path`. Do NOT pass large reports via `--content`.
- **For JSON queues:** You may use `--content '{"vulnerabilities": [...]}'`. Queue files are validated automatically.
- **Bash tool:** Use for creating directories, copying files, and other shell commands as needed.
- **Task Agent:** Mandatory coder-executor for IDOR sweeps, role escalation loops, and workflow bypass automation.
- **TodoWrite tool:** Essential for managing your exploitation task list. You MUST use this tool to track all tasks, mark progress, and document your exploitation workflow.