claude-code-commands

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill generates templates for Claude Code slash commands that interpolate untrusted user input ($ARGUMENTS) directly into shell command blocks, which could lead to command injection.
  • Ingestion points: Untrusted data enters via the $ARGUMENTS variable within the command templates defined in references/patterns.md (e.g., the Issue-Linked Command and DB Command templates).
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded shell meta-characters within the $ARGUMENTS string in the templates.
  • Capability inventory: The templates include capabilities for executing subprocesses via bash, specifically involving git, gh (GitHub CLI), grep, and npm commands in references/patterns.md.
  • Sanitization: The skill does not provide or recommend any sanitization, escaping, or validation logic for the $ARGUMENTS before they are used in shell commands, although references/validations.md check for the literal syntax of the variable itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 05:26 AM