stitch-mcp-get-project

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill retrieves configuration and project metadata from stitch.withgoogle.com, which is an official domain owned by a trusted organization.
  • [PROMPT_INJECTION]: The instructions include operational safeguards, such as requiring an explicit user mention of "Stitch" before tool invocation, which helps prevent unintended execution in complex dialogues.
  • [COMMAND_EXECUTION]: The skill uses the stitch*:* toolset and standard file tools (Read, Write) for their intended purposes of project management and metadata retrieval.
  • [PROMPT_INJECTION]: (Indirect) The skill processes project metadata like titles and theme descriptions. While this data is potentially user-controlled and represents a surface for indirect instructions, the integration targets a trusted service and does not exhibit malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:04 PM
Security Audit — agent-trust-hub — stitch-mcp-get-project