inboundfy-validador-email
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 process and validate untrusted external data, specifically email candidates and commercial briefs. This ingestion creates a surface where malicious instructions embedded in the input data could potentially override the agent's logic.
- Ingestion points: The skill explicitly reads 'Email candidato, brief e fontes comerciais' as its primary input (SKILL.md).
- Boundary markers: There are no instructions defining the use of delimiters or specific prompts to ignore instructions within the processed content to prevent accidental obedience.
- Capability inventory: The skill generates reports and interacts with other components of the Inboundfy framework (e.g.,
inboundfy-base-validadorandinboundfy-especialista-email). - Sanitization: The instructions do not include any steps for sanitizing, escaping, or filtering the external content before it is processed by the agent.
Audit Metadata