marketer-github

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes gh (GitHub CLI) and git commands to manage repositories, including cloning, branch creation, committing changes, and opening Pull Requests. These operations are conducted within the standard context of developer automation.
  • [PROMPT_INJECTION]: Potential for indirect prompt injection through repository content.
  • Ingestion points: The skill clones user-controlled repositories and reads HTML files to identify injection points for the WebMCP script.
  • Boundary markers: There are no boundary markers or instructions to ignore embedded commands when processing the files from the cloned repository.
  • Capability inventory: The agent has access to gh and git tools, which provide capabilities for network access and repository modification.
  • Sanitization: No sanitization or validation of the files read from the repository is performed before they are processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill configures the user's website to load a remote script from https://cdn.10x.in/webmcp.js. This script is delivered via a CDN and is intended to execute in the browsers of site visitors to provide personalization features.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 10:10 PM
Security Audit — agent-trust-hub — marketer-github