inboundfy-growth-relacoes-publicas
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from various project files and external research materials, which could potentially contain adversarial instructions aimed at influencing the agent's behavior.
- Ingestion points: The skill reads files from the
.inboundfy/configuration directory, project-specific sources (fontes-projeto.md), and external research items stored in the "acervo" (repository). - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple backticks) to isolate content from these external files when they are interpolated into the prompt.
- Capability inventory: The skill is authorized to write and update local files (as detailed in the 'Idempotency' section) and can trigger other skills like
inboundfy-copy-edicaoto process text. - Sanitization: The workflow includes mandatory review steps using specialized skills (
inboundfy-anti-slopandinboundfy-copy-edicao) which serve as a mitigation against poor quality or malicious content.
Audit Metadata