inboundfy-especialista-webinar
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external webinar briefs which can contain untrusted user-provided instructions.
- Ingestion points: The skill reads input from a brief file, as specified in the Entrada esperada section of SKILL.md and examples in REFERENCIA.md.
- Boundary markers: There are no explicit delimiters (such as XML tags or triple quotes with warnings) or instructions to ignore embedded commands used when reading input briefs.
- Capability inventory: The skill has the capability to write Markdown files to the local file system (e.g., paths defined in context/canais.md) and chain execution to other skills such as inboundfy-validador-webinar and inboundfy-planejamento.
- Sanitization: No sanitization or validation of the input brief content is performed before it is used to generate copy.
Audit Metadata