stitch-mcp-upload-design-md

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to use the Bash tool to execute the base64 command on the local filesystem. While intended for encoding, the availability of a shell tool allows for broader command execution capabilities.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the DESIGN.md file it processes.
  • Ingestion points: Local file DESIGN.md is read and its content is processed for Base64 encoding and API upload.
  • Boundary markers: There are no boundary markers or instructions to treat the file content as data only, potentially allowing embedded instructions to be executed by the agent.
  • Capability inventory: The skill possesses Bash access and the ability to interact with the stitch API tools, which could be abused if the agent follows malicious instructions in the design file.
  • Sanitization: The skill does not implement any sanitization or validation of the markdown content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 07:59 PM
Security Audit — agent-trust-hub — stitch-mcp-upload-design-md