animated-numbers
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a template ('brief') that interpolates user-provided data such as numerical figures and spoken words to be processed by a downstream agent (Claude Code).
- Ingestion points: User-provided values and timing words from Step 1 are directly inserted into the build brief in Step 2.
- Boundary markers: The template does not utilize delimiters or escape sequences to separate the user-provided strings from the instructions provided to the agent.
- Capability inventory: The intended downstream agent (Claude Code) has capabilities to modify project files such as video.js and words.js.
- Sanitization: The skill does not instruct the agent to validate or sanitize the input strings before including them in the executable context.
Audit Metadata