hunt-laravel
Hunt Laravel specific vulnerabilities — Debug mode leakage (APP_DEBUG=true exposes full stack trace + env vars), Laravel Telescope/Horizon dashboard unauthorized access, Ignition RCE (CVE-2021-3129), Signed URL manipulation, Queue Worker abuse, mass assignment via Eloquent, deserialization via cookies, .env file exposure. Use when target runs Laravel (PHP) — detected via X-Powered-By, Laravel session cookies, or /storage/ paths.
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
E004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
The document is an explicit exploit playbook giving step-by-step commands and tooling to discover, exfiltrate secrets (APP_KEY, logs, tokens), forge session cookies, and achieve remote code execution and account takeover on Laravel targets.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
The skill explicitly instructs cloning and running an exploit repository from GitHub (https://github.com/ambionics/laravel-ignition-rce), which is a third‑party public exploit tool intended to perform RCE against targets.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The document explicitly provides actionable, runnable exploit steps and tooling to achieve unauthorized remote code execution, session-cookie forging, and sensitive-data exfiltration (e.g. git clone + php exploit for Ignition RCE, curl POST to /_ignition/execute-solution, phpggc + cookie forge), showing clear malicious intent and viable runtime mechanisms.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill explicitly fetches and prints .env/APP_KEY values and instructs passing APP_KEY as a command-line argument (and to echo it / use it to sign cookies), which requires the agent to read and output secret values verbatim, enabling exfiltration.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill explicitly runs "git clone https://github.com/ambionics/laravel-ignition-rce" at runtime and then executes the downloaded exploit (php /tmp/laravel-rce/exploit.php), so the external GitHub URL fetches and supplies remote code that is executed.
- Repository
elementalsouls/Claude-BugHunter
- Revision
7d10e74
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.