inboundfy-atribuicao
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources including conversion reports, channel tools, and customer contact information, which serves as an ingestion point for untrusted content.
- Ingestion points: The skill reads external files such as
processado.mdfrom theacervo/directory and various datasets including UTMs, contact lists, and tool-specific reports. - Boundary markers: The instructions lack specific requirements for the agent to use delimiters (e.g., XML tags or unique markers) when interpolating external data into its context, increasing the risk that the agent might interpret data as instructions.
- Capability inventory: The skill instructions explicitly authorize the agent to "create or alter any artifact" and perform file operations to deliver reports and updated records.
- Sanitization: There are no documented steps for validating, filtering, or escaping the external inputs before they are processed by the agent.
Audit Metadata