github-issues

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of markdown documentation and does not contain any executable code or scripts.\n- [NO_CODE]: All skill functionality is implemented through natural language instructions guiding the agent to use external MCP tools.\n- [SAFE]: No hardcoded credentials, sensitive file paths, or unauthorized network patterns were found in the skill files.\n- [PROMPT_INJECTION]: The skill defines a workflow for reading and writing GitHub issues, which presents a surface for indirect prompt injection.\n
  • Ingestion points: Issue data is retrieved through MCP tools mcp__github__get_issue, mcp__github__search_issues, and mcp__github__list_issues.\n
  • Boundary markers: Absent; there are no specific instructions to the agent to disregard commands embedded within the retrieved issue bodies.\n
  • Capability inventory: The skill utilizes write-capable tools including mcp__github__create_issue, mcp__github__update_issue, and mcp__github__add_issue_comment.\n
  • Sanitization: Absent; the instructions do not implement any validation or filtering of the content retrieved from external GitHub issues.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 10:12 AM