skills/n8n-io/n8n/n8n:create-issue/Gen Agent Trust Hub

n8n:create-issue

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh CLI for issue creation. The instruction template employs a quoted heredoc (<<'EOF') for the issue body, which is a security best practice to prevent shell interpolation of the content. While the title is placed in double quotes, the overall design favors safe execution via the agent.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data as it processes user-provided descriptions and goal statements to populate ticket fields. It also incorporates external data from the Notion MCP.
  • Ingestion points: User input strings ($ARGUMENTS and conversation history) and Notion search results.
  • Boundary markers: The skill lacks explicit boundary delimiters for interpolated strings, relying instead on markdown templates.
  • Capability inventory: File system interaction (implicit via CLI), network operations (GitHub/Linear APIs), and data retrieval (Notion).
  • Sanitization: The skill mitigates risks by requiring the agent to present a full preview and wait for explicit user confirmation before the ticket or issue is created.
  • [SAFE]: The skill targets official vendor repositories (n8n-io/n8n) and utilizes well-known, trusted platforms (GitHub, Linear, Notion) for its primary functionality. All external references are consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 04:39 PM
Security Audit — agent-trust-hub — n8n:create-issue