inboundfy-growth-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external public documents and project collections to generate onboarding plans, creating a potential surface for indirect prompt injection.
- Ingestion points: Data is ingested from project-specific collections ("acervo"), external public documents, and user-provided objectives as defined in the 'Entrada esperada' section of SKILL.md.
- Boundary markers: The skill includes instructions to confirm intentions and separate confirmed facts from hypotheses (Step 1 and Step 3 in the Fluxo section of SKILL.md).
- Capability inventory: The skill is capable of creating and updating artifacts/files based on the processed data, as noted in the 'Idempotência' section of SKILL.md.
- Sanitization: The workflow incorporates a review process using specialized skills like 'inboundfy-anti-slop' and 'inboundfy-copy-edicao' to validate content before final output.
Audit Metadata