hackerone-brain-mcp-server

Warn

Audited by Snyk on Jul 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). Yes—runtime fetches HackerOne program policy and disclosed reports via the MCP server (fetch to https://api.hackerone.com/...), then returns them as readable text (JSON.stringify(data, ...)) which Claude ingests into its LLM context through the MCP tool response.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime fetches to the HackerOne API (e.g., https://api.hackerone.com/v1 and the program/report endpoints) and injects the returned program policy and disclosed-report data directly into the agent's context, which will directly control prompts/behavior.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 10, 2026, 10:48 PM
Issues
2