known-errors
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to treat tool schemas and structured error returns as authoritative sources of information. This identifies an ingestion surface for data that could theoretically be manipulated by external tools, though it is consistent with the skill's primary purpose and vendor context.
- Ingestion points: MCP tool schemas and returned structured errors (SKILL.md).
- Boundary markers: Not explicitly specified.
- Capability inventory: Media import, mutation retries, and motion graphic generation.
- Sanitization: Not explicitly described.
Audit Metadata