hyva-theme-list

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script list_hyva_themes.sh which utilizes the find utility to traverse project directories. This is a standard and safe operation for its stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface as it reads directory names and file paths from the local file system and outputs them to the agent's context. An attacker could potentially influence the agent by creating maliciously named files or directories, although the risk is limited given the skill's read-only nature.
  • Ingestion points: The shell script scans the directory structure of app/design/frontend and vendor for Magento theme markers.
  • Boundary markers: The script does not use explicit boundary markers or delimiters for its output.
  • Capability inventory: The skill is restricted to file system reading via find and bash. It does not perform network operations or file writing.
  • Sanitization: No sanitization is performed on the discovered directory paths before they are echoed to the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:40 AM
Security Audit — agent-trust-hub — hyva-theme-list