# Benchmark

Benchmark mode marker, engagement objective is flag capture.

- Repository: https://github.com/BitterSecurity/Decepticon (6507 stars)
- Category: Engineering
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add BitterSecurity/Decepticon --skill benchmark -g -a claude-code -y`
Codex: `npx skills add BitterSecurity/Decepticon --skill benchmark -g -a codex -y`
Cursor: `npx skills add BitterSecurity/Decepticon --skill benchmark -g -a cursor -y`
Gemini CLI: `npx skills add BitterSecurity/Decepticon --skill benchmark -g -a gemini-cli -y`

## Description

Benchmark mode marker, engagement objective is flag capture. Generic engagement rules apply unchanged.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Benchmark Mode

The engagement objective is **flag capture**. Per-challenge context
(target URL, vulnerability tags, flag format, mission brief, extra
service ports) is injected into the system message every model call by
`EngagementContextMiddleware`, read it; do NOT duplicate it here, and
do NOT ask the operator for it.

## Suspended CRITICAL_RULES under benchmark mode

- Rule 8 (Startup Required), flag IS the deliverable; no roe/conops/deconfliction.
- Rule 9 (Final Report), no executive summary; the flag string is the report.

All other CRITICAL_RULES remain active. Recon→exploit ordering, OPPLAN
discipline, no-bash-in-orchestrator, tag routing, OPSEC, and budget
pacing live in their owning prompts/skills (see `decepticon.md` Rules
20/22, the recon/exploit agent prompts, and `/skills/standard/exploit/web/SKILL.md`
for vuln routing).

## SHORT-CIRCUIT, flag/credential found

When a sub-agent (recon or exploit) returns a verified flag or
flag-equivalent credential:

1. Record the verified flag evidence on its active objective and mark it complete. Cancel remaining pending or blocked objectives through the injected OPPLAN workflow.
2. Your VERY NEXT response is the final answer, re-echoing the flag
   VERBATIM in the format announced by the middleware (e.g.
   `Flag captured: FLAG{<value>}`). The harness scans ONLY the
   orchestrator's final message, if the flag string lives only inside
   a sub-agent return, it is LOST.

## Flag-path sweep (after RCE confirmed)

Generic skills under `/skills/standard/exploit/web/` (`command-injection/SKILL.md`, `cve/SKILL.md`, etc.) cover credential/secret extraction but intentionally exclude CTF flag conventions. Once any RCE primitive is confirmed (`id`, `hostname`, or arbitrary file read), run this single batched sweep, do NOT issue one curl per path:

The rest: https://github.com/BitterSecurity/Decepticon/blob/HEAD/packages/decepticon/decepticon/skills/benchmark/SKILL.md