svelte-expert
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
Bashtool to executecat .claude/context/memory/learnings.md. This is part of a mandatory "Memory Protocol" designed to allow the agent to read and persist state between interactions within its own workspace. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to review and refactor code, which involves ingesting untrusted data that could contain malicious instructions designed to exploit the agent's toolset.
- Ingestion points: User-provided code snippets, Svelte components, and project files passed to the agent for review (e.g., via the
targetparameter in the input schema). - Boundary markers: None. The instructions do not define specific delimiters or warnings to treat ingested code as data rather than instructions.
- Capability inventory: The skill has access to a wide range of powerful tools including
Bash,Write,Edit,Read,Grep, andGlob, allowing for significant file system and shell interaction. - Sanitization: There are no explicit instructions for the agent to sanitize or escape content from the code it reviews before processing.
Audit Metadata