bug-bounty

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). The document contains explicit, step‑by‑step offensive instructions and proof‑of‑concepts for secret exfiltration, RCE, SSRF, GitHub Actions exploitation, and other exploit chains that enable harmful actions.

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

• Third-party content exposure detected (medium risk: 0.30). In “CI/CD Pipeline — GitHub Actions Security” the workflow instructs reading attacker-controlled GitHub event fields (e.g., github.event.issue.title, github.event.issue.body, github.event.pull_request.body, github.event.comment.body, commit messages) and using them in AI agent prompts (prompt injection via workflow context, plus agent execution depending on triggers).

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

• Potentially malicious external URL detected (high risk: 0.90). The INSTALLATION section includes commands that fetch the skill file used by the agent (git clone https://github.com/shuvonsec/claude-bug-bounty.git and curl https://raw.githubusercontent.com/shuvonsec/claude-bug-bounty/main/SKILL.md), which would load remote content that directly controls the agent's prompts/instructions.