inboundfy-validador-infografico-imagem
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to ingest and process external content including project briefs, approved copy, and various context files.
- Ingestion points: The skill reads files from the
context/directory (e.g.,canais.md,marca-voz.md), as well as external 'briefs' and 'approved copy' inputs as described inSKILL.md. - Boundary markers: The instructions do not explicitly define boundary markers or delimiters to separate instructions from untrusted external data during processing.
- Capability inventory: The skill generates validation reports and triggers other framework components like
inboundfy-base-validador. - Sanitization: There is no evidence of sanitization, filtering, or escaping of the external content before it is processed by the agent.
Audit Metadata