ae-data-driven
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns such as direct prompt injection, credential exfiltration, obfuscation, or persistence mechanisms were identified. The skill's operations are confined to the After Effects environment via a specialized toolset.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (CSV, TSV, JSON) which presents a theoretical attack surface. Ingestion points: Data is imported using ae_import_file or read by the agent (SKILL.md). Boundary markers: The instructions mandate inspecting the data ("look at the data before you build anything") before processing. Capability inventory: The skill uses tools for project manipulation (ae_shape, ae_text, ae_set_property, ae_batch) and rendering (ae_render_frame). Sanitization: Explicit guidance is provided to clean data, including encoding checks, trimming whitespace, and type conversion (Number()).
Audit Metadata