gemdesign-skill

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install and update the @gemdesign-ai/cli package from the NPM registry as a prerequisite for its operation.
  • [COMMAND_EXECUTION]: The skill uses shell commands, including npm for package management and the gemdesign CLI for authentication, app management, and starting a local preview server.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which creates a potential surface for indirect prompt injection.
  • Ingestion points: The skill reads user-provided requirements documents (PRDs) and fetches existing HTML content from the platform using the page get command as described in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions that might be embedded within the requirements documents.
  • Capability inventory: The skill has the ability to execute shell commands (npm, gemdesign), manage a local server process, and write HTML and metadata files to the local file system.
  • Sanitization: The instructions do not specify any sanitization, validation, or escaping of the content ingested from requirements documents before it is processed to generate design prototypes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:38 PM
Security Audit — agent-trust-hub — gemdesign-skill