stitch-swiftui-components
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
scripts/fetch-stitch.shto download content from user-provided URLs or Stitch API endpoints usingcurl. - [COMMAND_EXECUTION]: The agent is instructed to execute a local bash script to perform network fetching and file management.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted HTML data from external URLs and local files, creating a vulnerability to indirect prompt injection if the source design contains malicious instructions.
- Ingestion points: The agent reads
temp/source.html, which is populated from external sources. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish layout metadata from potential natural language instructions in the HTML.
- Capability inventory: The skill possesses the
Writetool to create source code files and theBashtool to run scripts. - Sanitization: There is no evidence of validation or sanitization applied to the source HTML before it is interpreted for code generation.
Audit Metadata