Skills
skills/full-stack-skills/stitch-skills/stitch-mcp-create-project/Gen Agent Trust Hub

stitch-mcp-create-project

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A comprehensive review of the skill's instructions, examples, and license revealed no malicious patterns. There are no attempts at prompt injection, obfuscation, or persistence.
  • [COMMAND_EXECUTION]: The skill uses the create_project tool within the stitch namespace, which is explicitly permitted in the frontmatter. The tool's purpose is to manage project containers based on user-provided titles, which is a benign and scoped operation.
  • [DATA_EXFILTRATION]: The skill does not access sensitive files (e.g., SSH keys, AWS credentials) or perform unauthorized network requests. All data handling is local to the project creation workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:04 PM
Security Audit — agent-trust-hub — stitch-mcp-create-project