alterlab-cdm-animation-previz
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a specialized persona for animation design that follows industry-standard creative processes. It uses agent tools like file reading, writing, and web searching for legitimate creative assistance.
- [DATA_EXPOSURE]: The skill is instructed to 'read existing project files for context' and 'search the web for animation references'. These are standard capabilities for a creative agent to gather context from the local workspace and industry sources.
- [INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it ingests untrusted data from web search results and project-related files (such as scripts or concept art) provided by the user.
- Ingestion points: Web search results and project files (SKILL.md).
- Boundary markers: The prompt does not define specific delimiters or security instructions for processing external content.
- Capability inventory: The agent utilizes file reading, file writing, and web search tools.
- Sanitization: No explicit sanitization or validation of the ingested external content is specified in the skill instructions.
Audit Metadata