inboundfy-validador-infografico
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it evaluates external copy and briefs. This presents a potential for indirect prompt injection if the input content contains instructions aimed at misleading the validator. The impact is mitigated by the skill's restricted set of capabilities.
- Ingestion points: Inbound copy candidate, brief, and project data as specified in
SKILL.md. - Boundary markers: The skill operates within a framework-defined "Contrato de artefato" which provides structural constraints, though no explicit markdown delimiters are specified for the input text.
- Capability inventory: The skill is limited to reading project-specific markdown files (
.inboundfy/,context/,../_shared/) and generating report files in defined locations. It lacks network access or general shell execution permissions. - Sanitization: Input content is read directly for comparison against standards without specific escaping or sanitization protocols mentioned.
Audit Metadata