stitch-svelte-components

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes a shell script scripts/fetch-stitch.sh designed to download content from remote URLs using curl. The main instructions direct the agent to retrieve download URLs for design assets from a tool and pass them to this script for local storage.
  • [COMMAND_EXECUTION]: The skill requires the execution of several shell commands, including npm install for dependency management and npm run dev for local development and verification. It also executes the local scripts/fetch-stitch.sh script.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes HTML content from external, dynamic URLs to guide the generation of Svelte components.
  • Ingestion points: Design HTML downloaded via scripts/fetch-stitch.sh as instructed in SKILL.md Step 1.
  • Boundary markers: None. The skill does not implement delimiters or instructions to ignore embedded commands within the fetched HTML.
  • Capability inventory: The skill has capabilities for file system writes, shell command execution (Bash), and network downloads (curl).
  • Sanitization: No validation or sanitization is performed on the downloaded HTML content before it is processed by the agent to generate component code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 02:42 AM