inboundfy-processar-acervo
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data and uses it to generate multiple output files and drive downstream actions, representing an attack surface for indirect prompt injection.\n
- Ingestion points: The skill processes raw material from
bruto.mdas its primary input, as described inSKILL.mdandREFERENCIA.md.\n - Boundary markers: No explicit delimiters, boundary markers, or specific instructions to disregard embedded commands in the input data are present in the processing flow.\n
- Capability inventory: The skill has the capability to write multiple files (
processado.md,faq.md, and audit reports) and triggers the execution of the downstream skillinboundfy-extrair-faq.\n - Sanitization: While the skill removes 'noise' and 'slop', there is no evidence of security-focused sanitization or validation to prevent instructions in the source text from influencing agent behavior.
Audit Metadata