inboundfy-dados-estruturados
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes facts and information from external sources (websites, products, organizations) to create structured data, which introduces a surface for potentially malicious instructions to be embedded in the processed data.
- Ingestion points: As described in the 'Entrada esperada' section of
SKILL.md, the skill receives confirmed facts from external sources like site content and articles. - Boundary markers: The instructions mandate the separation of confirmed facts from hypotheses and open questions. Additionally,
REFERENCIA.mdprovides a structured Markdown and YAML template to constrain the agent's output format. - Capability inventory: The skill is capable of reading project-specific configuration files from the
.inboundfy/directory and writing or updating artifacts as part of its output process. - Sanitization: The workflow incorporates integrated revision steps, such as
inboundfy-anti-slopandinboundfy-copy-edicao, to review and validate the generated material before it is finalized.
Audit Metadata