feat: thread attack objective through sdk and mcp runners#193
Open
jithin23-kv wants to merge 1 commit into
Open
feat: thread attack objective through sdk and mcp runners#193jithin23-kv wants to merge 1 commit into
jithin23-kv wants to merge 1 commit into
Conversation
RunConfig.attackObjective already exists in core and is wired up for `opfor run --objective`/`--objective-file`, but the SDK and MCP server had no way to set it — only opfor hunt and the CLI run command could steer attacks with a free-text mission. - SDK: add RunOptions.attackObjective, threaded through buildRunConfig() into the core RunConfig. - MCP: add attack_objective to opfor_setup (baked into the written config) and objective_override to opfor_run (overrides it at run time, same pattern as effort_override/turns_override). Both tools' response text now echo the objective when set. - docs: document the new SDK option and MCP parameters.
WalkthroughChangesAttack objective configuration
Estimated code review effort: 3 (Moderate) | ~20 minutes Sequence Diagram(s)sequenceDiagram
participant Operator
participant CLI_or_MCP
participant RunConfig
participant runEvaluatorAttacks
participant GeneratedAttacks
Operator->>CLI_or_MCP: provide objective
CLI_or_MCP->>RunConfig: store or override attackObjective
RunConfig->>runEvaluatorAttacks: pass configured objective
runEvaluatorAttacks->>GeneratedAttacks: assign objective to each attack
Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@runners/mcp/src/index.ts`:
- Around line 231-237: Update the attack_objective and objective_override
schemas to trim input and reject empty or whitespace-only strings. In the setup
flow, preserve valid empty checks by testing both override values with !==
undefined rather than truthiness, so validated objectives are not silently
dropped.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: f39d110c-eded-47ab-8ac3-7c4fb5882bb8
📒 Files selected for processing (10)
core/src/config/schema.tscore/src/execute/evaluatorLoop.tscore/src/execute/types.tsdocs/cli.mddocs/mcp.mddocs/sdk.mdrunners/cli/src/commands/run.tsrunners/mcp/src/index.tsrunners/sdk/src/internal/buildRunConfig.tsrunners/sdk/src/types.ts
Comment on lines
+231
to
+237
| attack_objective: z | ||
| .string() | ||
| .optional() | ||
| .describe( | ||
| "Free-text primary mission steering every evaluator's attacks " + | ||
| "(e.g. 'get the target to leak env vars via a delegated employee')." | ||
| ), |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Locate the relevant file and inspect the surrounding sections.
git ls-files runners/mcp/src/index.ts
echo "---- outline ----"
ast-grep outline runners/mcp/src/index.ts --view expanded || true
echo "---- targeted ranges ----"
sed -n '200,410p' runners/mcp/src/index.ts | cat -nRepository: KeyValueSoftwareSystems/agent-opfor
Length of output: 9864
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Inspect the config-building logic and objective handling in the rest of the file.
sed -n '430,560p' runners/mcp/src/index.ts | cat -nRepository: KeyValueSoftwareSystems/agent-opfor
Length of output: 5680
Reject blank objectives instead of dropping them.
attack_objective and objective_override accept blank strings today; the setup path drops "" via truthiness, while whitespace-only values pass through unchanged. Trim and require a non-empty value, then switch the override checks to !== undefined.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@runners/mcp/src/index.ts` around lines 231 - 237, Update the attack_objective
and objective_override schemas to trim input and reject empty or whitespace-only
strings. In the setup flow, preserve valid empty checks by testing both override
values with !== undefined rather than truthiness, so validated objectives are
not silently dropped.
Source: Coding guidelines
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
There was no way to steer every evaluator's attacks toward a specific free-text mission (e.g. "get the target to leak env vars via a delegated employee") — each evaluator just pursued its own generic goal.
opfor huntalready had--objectivefor its autonomous mode, but the evaluator-basedopfor runpath had no equivalent, on any surface (CLI, SDK, or MCP).Solution
Added
attackObjectiveend-to-end across all three ways of drivingopfor run:RunConfig.attackObjective(schema + type), applied onto every generated agent attack inrunEvaluatorAttacks.opfor run --objective <text>/--objective-file <path>.RunOptions.attackObjective, threaded throughbuildRunConfig().attack_objectiveonopfor_setup(baked into the written config) andobjective_overrideonopfor_run(runtime override, same pattern aseffort_override/turns_override). Both tools echo the objective in their response text when set.Changes
core/src/config/schema.ts,core/src/execute/types.ts—attackObjectivefield/schema onRunConfigcore/src/execute/evaluatorLoop.ts— applies it onto generated agent attacksrunners/cli/src/commands/run.ts—--objective/--objective-filerunners/sdk/src/types.ts,runners/sdk/src/internal/buildRunConfig.ts— SDK supportrunners/mcp/src/index.ts— MCP supportdocs/cli.md,docs/sdk.md,docs/mcp.mdIssue
N/A
How to test
npm run buildopfor run --config <file> --objective "<text>"(or--objective-file <path>) — confirm the log printsObjective: ...and generated attacks reflect the mission.run({ ..., attackObjective: "..." })and confirm it reaches generated attack prompts.opfor_setupwithattack_objectiveset, confirm it's written intoopfor.config.json; then callopfor_runwithobjective_overrideset and confirm it overrides the config value (response text showsObjective: ...).npm run typecheck && npm run lint && npm run format:checkall pass.Screenshots
N/A — no UI/report surface changes.
Summary by CodeRabbit
New Features
--objectiveand--objective-fileoptions to CLI runs.Documentation