rotating-text
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill cycles words provided via the 'data-words' attribute, which represents an ingestion surface for untrusted external content.
- Ingestion points: The 'data-words' attribute is read by the attach function in 'rotating-text.js' to define the sequence of words to be displayed.
- Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the 'data-words' content.
- Capability inventory: The skill is dependency-free and does not possess capabilities for network requests, file system modification, or command execution.
- Sanitization: The implementation uses '.textContent' to update the UI, which treats the input as literal text and prevents script execution (XSS), though it does not block the agent from interpreting the text as instructions if it reads the rendered output.
Audit Metadata