inboundfy-growth-parcerias
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from multiple external sources, including user-provided objectives and various project context files (
.inboundfy/context/*.md,.inboundfy/estrategia.md, etc.), creating a surface for indirect prompt injection. - Ingestion points: The skill reads from
.inboundfy/context/,.inboundfy/estrategia.md,.inboundfy/fontes-projeto.md, and receives user inputs like 'objetivo' and 'persona'. - Capability inventory: The skill's primary function is content generation and coordination between other skills (
inboundfy-anti-slop,inboundfy-copy-edicao). No shell or direct network capabilities are identified. - Boundary markers: The instructions lack explicit directives to use delimiters or ignore instructions embedded within the processed data.
- Sanitization: No sanitization or validation of the input data is mentioned before processing.
Audit Metadata