ghost-proxy

Fail

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides an installation command that fetches and runs a script from the vendor's repository: curl -sfL https://raw.githubusercontent.com/ghostsecurity/reaper/main/scripts/install.sh | bash. This is used to set up the Reaper CLI tool.
  • [COMMAND_EXECUTION]: The skill executes various reaper shell commands to manage the proxy lifecycle (start/stop), view recent logs, and perform targeted searches of captured traffic.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by intercepting live HTTP/HTTPS traffic between clients and servers.
  • Ingestion points: Captured traffic is displayed to the agent via reaper logs, reaper search, and reaper get <id> commands.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to disregard commands embedded within the captured traffic.
  • Capability inventory: The skill can start and stop background processes, read/write files in ~/.reaper/, and capture network traffic.
  • Sanitization: No sanitization, filtering, or escaping of the raw HTTP content is specified before it is provided to the agent for analysis.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/ghostsecurity/reaper/main/scripts/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 29, 2026, 01:31 PM
Security Audit — agent-trust-hub — ghost-proxy