inboundfy-copy-oferta
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data and user inputs to generate marketing copy, creating a surface for indirect prompt injection. Ingestion points: Files in .inboundfy/context/, .inboundfy/framework/, and the acervo/ directory. Boundary markers: None identified; instructions do not explicitly tell the agent to ignore instructions embedded in the project files. Capability inventory: No dangerous tools or system capabilities (shell, network, etc.) are utilized by the skill. Sanitization: No input validation logic is present. Mitigation: Wrap external content in delimiters with explicit instructions for the AI to ignore any directives contained within that data.
Audit Metadata