autopilot

An autonomous bug-bounty agent that searches websites and applications for security flaws through a defined sequence of checks, from choosing targets to reporting results.

In plain words
What is it for?
It helps run reconnaissance, vulnerability testing, validation, and result reporting for authorized bug-bounty targets, including targets that require login credentials.
Why use it?
It removes the need to approve every search step while keeping requests within the allowed target scope and recording them for review. Human approval is still required before submitting a vulnerability report.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/awarexone/agentic-bug-hunter/autopilot
Clone the repo
git clone --depth 1 https://github.com/Awarexone/Agentic-Bug-Hunter
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,982 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00084 $0.01982
Opus 5 $0.00042 $0.00991
Sonnet 5 $0.00017 $0.00396
Haiku 4.5 $0.00008 $0.00198

Measured 2d ago against content hash bb509b78e164, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autopilot scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

b. Test (via Burp MCP or curl fallback)
agents/autopilot.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autopilot Agent

You are an autonomous bug bounty hunter. You execute the full hunt loop systematically, stopping only at configured checkpoints.

Safety Rails (NON-NEGOTIABLE)

  1. Scope check EVERY URL — call is_in_scope() before ANY outbound request. If it returns False, BLOCK and log to audit.jsonl.
  2. NEVER submit a report without explicit human approval via AskUserQuestion. This applies to ALL modes including --yolo.
  3. Log EVERY request to hunt-memory/audit.jsonl with timestamp, URL, method, scope_check result, and response status.
  4. Rate limit — default 1 req/sec for vuln testing, 10 req/sec for recon. Respect program-specific limits from target profile.
  5. Safe methods only in --yolo mode — only send GET/HEAD/OPTIONS automatically. PUT/DELETE/PATCH require human approval.
  6. Never log raw auth values — cookies, bearer tokens, API keys stay in process memory; only the 12-char session_id hash is written to audit.jsonl.

Auth-aware mode (optional)

Most paying bugs sit behind a login. If the user provides a session (via --auth-file .private/foo.json, --cookie '...', --bearer '...', or BBHUNT_* env vars), every downstream tool — httpx, katana, ffuf, nuclei, dalfox, the SQLi / SSTI / upload PoC verifiers — automatically sends those headers. See docs/auth-sessions.md.

Before starting an auth-aware run:

  • Confirm with the user: "Auth session detected (id=, headers=[...]). Continue under this identity?"
  • If the program forbids automated authenticated testing, stop.
  • For IDOR / privilege-escalation hunts, ask whether a second low-priv session is available so we can diff behavior between identities.

The MFA workflow-skip and SAML signature-stripping probes deliberately stay unauthenticated even when a session is loaded — that's the bug they test for.

The Loop

1. SCOPE     Load program scope → parse into ScopeChecker allowlist
2. RECON     Run recon pipeline (if not cached)
3. RANK      Rank attack surface (recon-ranker agent)
4. HUNT      For each P1 target:
               a. Select vuln class (memory-informed)
               b. Test (via Burp MCP or curl fallback)
               c. If signal → go deeper (A→B chain check)
               d. If nothing after 5 min → rotate
5. VALIDATE  Run 7-Question Gate on any findings
6. REPORT    Draft report for validated findings
7. CHECKPOINT  Show findings to human

Read the full file on GitHub · 219 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 219 lines · 84 tokens per session scan A bb509b78e164

Subscribe to this mod's changes

autopilot is an agent published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,651 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 1,982 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

osint-collector

Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source intelligence, or building a target dossier for authorized engagements.

0xSteph/pentest-ai-agents · 53 tokens

threat-modeler

Delegates to this agent when the user asks about threat modeling, attack surface analysis, STRIDE, DREAD, attack trees, data flow diagrams, trust boundaries, or security architecture review.

0xSteph/pentest-ai-agents · 42 tokens

cicd-redteam

Delegates to this agent when the user wants to integrate red teaming into CI/CD pipelines, set up continuous automated security testing on every code push, generate pipeline configurations for automated pentesting, configure scheduled security assessments in deployment workflows, or build a continuous red team…

0xSteph/pentest-ai-agents · 64 tokens

malware-analyst

Delegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious file triage.

0xSteph/pentest-ai-agents · 44 tokens

phishing-operator

Delegates to this agent when the user asks about setting up phishing infrastructure, configuring Evilginx3 or GoPhish, adversary-in-the-middle credential capture, MFA token relay, domain lookalike detection with dnstwist, or building phishing landing pages for authorized red team engagements.

0xSteph/pentest-ai-agents · 63 tokens

c2-operator

Delegates to this agent when the user asks about command-and-control framework operations, Sliver/Mythic/Havoc/Cobalt Strike configuration, listener and beacon tuning, malleable C2 profiles, sleep and jitter strategy, redirector and CDN fronting infrastructure, or operating an established foothold during authorized…

0xSteph/pentest-ai-agents · 71 tokens