lottiefiles-animation-workflows
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external animation document data via the
engine_documenttool to determine its state and apply changes. This creates a potential surface where malicious instructions embedded within a document could attempt to influence the agent's behavior. - Ingestion points: Animation document content accessed via
engine_document(SKILL.md). - Boundary markers: The skill does not define specific delimiters for untrusted document content, though it instructs the agent to make the 'smallest requested change'.
- Capability inventory:
engine_exec(modifies documents),engine_export(writes files/assets),engine_job_result(inspects async output). - Sanitization: No explicit sanitization or filtering of document content is mentioned, although instructions prohibit exposing credentials or private data.
Audit Metadata