inboundfy-growth-comunidade
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface where untrusted user input is processed alongside file modification capabilities.
- Ingestion points: User-defined objectives, IDs, personas, and channels are ingested during the planning phase as described in SKILL.md.
- Boundary markers: Absent. The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) to isolate user-supplied input from the rest of the prompt context.
- Capability inventory: The skill is designed to read local configuration files and update existing files or briefs (e.g., in REFERENCIA.md).
- Sanitization: The skill references internal validation tools (inboundfy-anti-slop, inboundfy-copy-edicao) to review generated content before final delivery.
Audit Metadata