inboundfy-growth-influenciadores
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific documentation and external collection data, creating a potential vector for indirect instructions.
- Ingestion points: The skill reads from multiple files including
.inboundfy/estrategia.md,.inboundfy/context/documents, and user-provided 'acervo' (collection) IDs as specified in SKILL.md and REFERENCIA.md. - Boundary markers: There are no explicit instructions, delimiters, or warnings for the agent to treat content from these files as untrusted or to ignore instructions embedded within them.
- Capability inventory: The skill facilitates reading project context and writing new partnership briefs, which allows injected content to influence generated artifacts.
- Sanitization: Although the skill refers to
inboundfy-anti-slopfor validating copy, no specific sanitization or escaping protocols are defined for the variety of ingested data sources.
Audit Metadata