bb-local-toolkit

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). This document contains explicit, actionable instructions for secret exfiltration, RCE, cloud credential theft, CI/CD compromise, and other offensive operations enabling real-world attacks.

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

• Potentially malicious external URL detected (high risk: 0.90). The INSTALLATION steps fetch the skill content at runtime (which would control agent instructions) via git clone https://github.com/shuvonsec/claude-bug-bounty.git and curl https://raw.githubusercontent.com/shuvonsec/claude-bug-bounty/main/SKILL.md, so remote content directly controls the agent's prompts when installed.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill includes explicit post‑exploitation instructions that modify host state (e.g., "add SSH keys, modify sudoers", privileged docker chroot, core dumps and env exfiltration), which direct an agent to perform actions requiring elevated privileges and persist on the machine.