bug-bounty

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). These URLs point to a third‑party GitHub repository and its raw content which the SKILL explicitly instructs users to git-clone/curl — installing or executing code pulled from an unverified personal repo can deliver malware or backdoors.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document contains explicit, actionable instructions and PoCs for secret exfiltration, RCE via CI workflows, supply-chain poisonings, and persistent runner compromise — patterns that enable deliberate malicious abuse beyond benign research guidance.

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

• Potentially malicious external URL detected (high risk: 0.90). The INSTALLATION section instructs cloning/downloading remote skill content that the agent will load and use as its skill prompt (git clone https://github.com/shuvonsec/claude-bug-bounty.git and curl https://raw.githubusercontent.com/shuvonsec/claude-bug-bounty/main/SKILL.md), so these URLs fetch remote content that directly controls agent instructions at runtime.