skills/nvidia/openshell/create-spike/Gen Agent Trust Hub

create-spike

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes gh CLI commands to interact with GitHub repositories, including fetching labels and creating issues.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection vulnerability surface where user-supplied problem statements are processed and included in shell commands. 1. Ingestion points: User-provided problem descriptions (Step 1). 2. Boundary markers: Missing in the shell command templates used to create issues. 3. Capability inventory: The skill uses the gh CLI for repository interaction and network communication. 4. Sanitization: The skill does not implement validation or escaping for external input used in prompts or commands.
  • [EXTERNAL_DOWNLOADS]: The skill uses the gh CLI to download repository metadata (labels) from GitHub.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 02:27 PM
Security Audit — agent-trust-hub — create-spike