inboundfy-iniciar
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and forward the "original request" (pedido original) from a user or previous instruction to another skill.
- Ingestion points: The request enters via the main input described in
SKILL.mdandREFERENCIA.md. - Boundary markers: The instructions specify passing the request "without reformulating or removing context," but do not define strict security boundaries or delimiters to isolate potential instructions embedded in the user data.
- Capability inventory: The skill itself has no capabilities for file system writing, network operations, or shell command execution; its sole function is triggering a handoff to the
$inboundfyskill. - Sanitization: There is no evidence of input validation, filtering, or escaping of the user-provided request before it is passed downstream.
Audit Metadata