Agentic Bug Hunter is a terminal toolkit that uses AI to investigate security targets, test for vulnerabilities, validate findings, and write bug bounty reports. It is for ethical hackers submitting findings to platforms such as HackerOne, Bugcrowd, Intigriti, or Immunefi, and can resume previous sessions. The catalogue entries package commands, skills, agents, instructions, hooks, and settings for using the toolkit.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Awarexone/Agentic-Bug-Hunternpx agentmods add skills/awarexone/agentic-bug-hunter/argusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/awarexone/agentic-bug-hunter/argus)<a href="https://agentmods.dev/skills/awarexone/agentic-bug-hunter/argus"><img src="https://agentmods.dev/badge/skills/awarexone/agentic-bug-hunter/argus/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/awarexone/agentic-bug-hunter/argus"><img src="https://agentmods.dev/badge/skills/awarexone/agentic-bug-hunter/argus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 81 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 32 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Tool Misuse · line 41 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00166 | $0.01943 |
| Opus 5.5 | $0.00066 | $0.00777 |
| Sonnet 5.5 | $0.00033 | $0.00389 |
| Haiku 4.5 | $0.00017 | $0.00194 |
Grade A, and why
argus 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 1mo 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.
> `urllib` strips raw `\r\n` from URLs by design — the **encoded** variants are How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARGUS — THE ALL-SEEING SCANNER SUITE
Named for Argus Panoptes, the hundred-eyed giant. Six "eyes" that surface what ordinary scans miss: two of the most common web2 classes (CORS, CRLF), the NoSQL "db" surface, JWT forging, blind-bug confirmation via OOB (the eye that sees the invisible — unblocks an entire severity band), and automated LLM red-teaming. All pure-Python, no new deps. Core logic is offline-testable.
0. ROUTING — which tool for what
| Signal on the target | Tool / command |
|---|---|
API reflects Origin, or ACAO/ACAC headers seen |
/cors |
Param reaches a redirect / Location / log / response header |
/crlf |
JSON login or {user,pass} body, Mongo/Mongoose stack |
/nosqli |
Authorization: Bearer ey... / JWT in cookie or storage |
/jwt-scan |
| Suspected blind SSRF/XXE/SQLi/RCE (no in-band signal) | /oob |
| Chatbot / agent / LLM feature | /llm-redteam |
1. CORS — /cors
tools/cors_scanner.py https://api.target.com/me --cookie "session=..."
tools/cors_scanner.py -l recon/target.com/urls/api.txt --json
Sends crafted Origin headers, classifies Access-Control-Allow-Origin /
Access-Control-Allow-Credentials:
- CRITICAL — reflects attacker origin with
ACAC: true→ cookie-auth'd cross-origin read (account-data exfil). - HIGH —
nullorigin trusted with credentials. - MEDIUM — reflects without creds (exploitable when auth = non-cookie token), or trusts http downgrade.
- Probes suffix/prefix regex bypass (
target.com.evil,notarget.com) and subdomain trust (chains with takeover).
Always pass --cookie with a live session — the credentialed path is the win.
2. CRLF / host-header — /crlf
tools/crlf_scanner.py "https://target.com/r?u=x" --host-header
Injects encoded CRLF (%0d%0a, double-encoded, UTF-8 overlong %E5%98%8A%E5%98%8D)
trying to land Set-Cookie: crlftest=1 in the response. --host-header also tests
Host / X-Forwarded-Host / Forwarded injection and flags attacker-host
reflection in Location (password-reset poisoning). Impact: session fixation,
open redirect, cache poisoning, reset poisoning.
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.
- 1mo ago First seen · 143 lines · 166 tokens per session scan A 5a2803f30da1
argus is a skill published in the GitHub repository Awarexone/Agentic-Bug-Hunter (5,367 stars, last pushed 12d ago), licensed MIT. It adds 166 tokens to every session and 1,943 once invoked, about $0.0007 per session on Opus 5.5. 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.
Other skills, from other repositories
sast-gap-analyzer
Analyzes validation gaps in data flows. Takes traced flows and identifies where checks are missing, insufficient, or bypassable. The 'interaction reasoning' step — finds bugs that exist in the gaps between individually correct-looking code. MUST run on Opus. Use via /sast command.
sast-flow-tracer
Traces data flow from entry points to dangerous operations. Cross-file reasoning to determine which entries can reach which dangers, and what validation exists in between. MUST run on Opus for reasoning depth. Use via /sast command.
sast-hunter
Focused PoC builder for SAST candidates. Receives a SPECIFIC candidate vulnerability that survived adversarial validation. Writes a PoC, compiles, runs with ASan, confirms or rejects. Use via /sast command.
dast-devils-advocate
Adversarial validator for DAST findings. Attempts to DISPROVE each finding and DOWNGRADE severity. Catches inflated reports, unverified assumptions, and theoretical-only bugs. Dispatch after /validate PASS and before /report.
bugcrowd-reporting
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…
enterprise-vpn-attack
External SSL VPN / remote-access appliance attack matrix — Cisco ASA/AnyConnect, Fortinet FortiGate/FortiOS, Citrix NetScaler/ADC, Palo Alto GlobalProtect, Pulse Secure / Ivanti Connect Secure, SonicWall, F5 Big-IP. Covers version fingerprinting, CVE matrix (2018-2026), AAA backend identification, default credentials…