github-automation

Warn

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to connect to an external, third-party MCP endpoint at https://rube.app/mcp. This server provides the tool definitions and execution logic for the GitHub toolkit.
  • [COMMAND_EXECUTION]: The skill exposes highly sensitive administrative tools that can perform destructive actions. Evidence includes the availability of GITHUB_DELETE_A_REPOSITORY, which is permanent and irreversible, and GITHUB_UPDATE_BRANCH_PROTECTION, which can be used to bypass security controls. Although the documentation advises user confirmation, the agent has the technical capability to execute these commands.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from external sources and has powerful write capabilities.
  • Ingestion points: The skill reads external content through GITHUB_LIST_REPOSITORY_ISSUES, GITHUB_SEARCH_CODE, GITHUB_GET_REPOSITORY_CONTENT, and GITHUB_GET_A_PULL_REQUEST (all in SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are implemented when processing these data sources.
  • Capability inventory: The skill possesses extensive capabilities including deleting repositories, merging pull requests, and triggering CI/CD workflows via GITHUB_CREATE_A_WORKFLOW_DISPATCH_EVENT.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from GitHub before it is processed or used to inform subsequent automated actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 12:15 PM