Hunt HTML Injection — user-supplied input is rendered as raw HTML in the response without sanitisation, allowing an attacker to inject arbitrary HTML tags (but not necessarily JavaScript). Lower severity than XSS but enables phishing, UI manipulation, and credential harvesting via injected forms. Use when testing text-display surfaces (search results, profile fields, comments, error messages, feedback forms). For markup that executes JavaScript, escalate to hunt-xss.
81%
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
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.
This document contains explicit, actionable instructions for injecting HTML (including onerror payloads), methods for credential harvesting and phishing, and a described technique for exfiltrating secrets via dangling markup, which is clearly malicious guidance.
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 skill targets user-supplied input reflected/stored into HTML display surfaces (e.g., search boxes, comments, profile fields, error messages, contact forms) and thus the runtime workflow can ingest arbitrary outsider-authored free text directly from those fields and render it in responses.
elementalsouls/Claude-BugHunter
2f9a226
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.