stitch-mcp-list-projects
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified through the ingestion of external data.
- Ingestion points: The skill retrieves project names, titles, and timestamps from the
list_projectstool. - Boundary markers: No delimiters or specific instructions are provided to the agent to ignore or isolate natural language instructions that might be embedded in the project titles.
- Capability inventory: The skill environment allows access to
stitch*:*tools, providing a surface for actions that could be triggered by an injection. - Sanitization: There is no sanitization or verification process for the content of the project titles before they are presented to the user or used by the agent.
Audit Metadata