Use when the user says "run johnwick" / "/johnwick", hands you a bug-bounty target or scope and wants the full manual+recon+automated hunt run end-to-end, or asks to hunt a target with total coverage (every in-scope domain/subdomain, all JS, signup+login, then exploit and validate). Self-contained long-running orchestrator — recon, JS mining, auto-signup, and hunting for IDOR, SSRF, RCE, SSTI, XXE, SQLi, request smuggling, cache poisoning, race conditions, OAuth/JWT/SAML ATO, GraphQL, 403-bypass, and mobile are all built in via internal reference files (each grounded in disclosed paid HackerOne reports), with a zero-skip coverage ledger and a superpowers verification gate between every phase.
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required Phase 3 auto-signup path polls public temp-mail inboxes (mail.tm, 1secmail) and reads message text/HTML, which anyone can send to a guessable address, so an outsider can deliver text into a feed the workflow consumes without the agent selecting an item.
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.
The decisive boundary is the runtime calls to third-party temp-mail APIs (api.mail.tm and 1secmail.com) whose responses supply the signup domain, tokens, and message content the skill adopts for account creation; neither service is first-party verified, so this is a common/reputable unofficial dependency, medium.
Awarexone/Agentic-Bug-Hunter
82f4512
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.