bug-bounty

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). The repository contains detailed, operational instructions for discovering and exploiting vulnerabilities — including secret exfiltration via SSRF to cloud metadata and automated credential‑attack (password‑spray) workflows — which meaningfully enables harmful actions.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill documents an AI agent/hunt workflow that may read outsider-authored free text from recon outputs and crawled URLs/documents returned by targets (e.g., recon/crawl classification of URLs, and agent planning that uses those extracted contents), rather than restricting ingestion to trusted first-party sources.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's installation instructions fetch the skill content from external locations that directly control agent behavior (e.g., git clone https://github.com/shuvonsec/claude-bug-bounty.git and curl https://raw.githubusercontent.com/shuvonsec/claude-bug-bounty/main/SKILL.md to install the SKILL.md the agent will load), so remote content is required to provide the agent's prompts/instructions.