inboundfy-validador-newsletter
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and validate external content (newsletters, briefs, and sources), which presents a potential surface for indirect prompt injection if the processed content contains adversarial instructions.
- Ingestion points: Processes 'Newsletter candidata', 'brief', and 'fontes' as defined in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt instructions to separate untrusted data from system instructions.
- Capability inventory: Accesses local project files in .inboundfy/, context/, and _shared/ directories. It generates validation reports but does not perform network operations or execute arbitrary code.
- Sanitization: No specific sanitization or filtering of input content is described before the AI processes it.
- [COMMAND_EXECUTION]: The skill references the execution of internal framework tools such as 'inboundfy-setup' and 'inboundfy-base-validador'. These tools are part of the vendor's own ecosystem and are used for project initialization and baseline validation functions within the intended workflow.
Audit Metadata