inboundfy-copy-redacao
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where untrusted data could influence behavior. Evidence chain: (1) Ingestion points: The skill reads from multiple local files including bruto.md, processado.md, faq.md, base-editorial.md, and pesquisa.md as specified in SKILL.md. (2) Boundary markers: No explicit delimiters or instructions are provided to isolate untrusted content. (3) Capability inventory: The skill invokes internal utilities like inboundfy-setup and inboundfy-anti-slop and performs file-write operations for saving the generated copy. (4) Sanitization: No sanitization of ingested content is mentioned. This risk is mitigated by the skill's structured execution architecture.
- [EXTERNAL_DOWNLOADS]: The instructions reference internal platform tools such as inboundfy-setup and inboundfy-anti-slop. These are part of the local environment and do not involve executing code from untrusted external sources.
Audit Metadata