github-workflow

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its interaction with external, untrusted GitHub content.
  • Ingestion points: The skill reads and processes descriptions and content from GitHub issues, pull requests, and review threads (SKILL.md).
  • Boundary markers: No delimiters or specific instructions to ignore embedded commands are present in the workflow for processing external content.
  • Capability inventory: The skill utilizes GitHub MCP tools and the gh CLI to create branches, commits, and modify issues or pull requests (SKILL.md).
  • Sanitization: No sanitization or validation logic is defined for the ingested GitHub data.
  • [COMMAND_EXECUTION]: Use of CLI tools. The skill explicitly instructs the agent to use the gh (GitHub) CLI as a fallback when standard MCP tools are insufficient (SKILL.md).
  • [NO_CODE]: The skill consists entirely of markdown instructions and safety guidelines, with no accompanying scripts or executable files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 08:06 PM
Security Audit — agent-trust-hub — github-workflow